Gokhan Tur

Jack FitzGerald, Christopher Hench, Charith Peris et al. · amazon-science

We present the MASSIVE dataset--Multilingual Amazon Slu resource package (SLURP) for Slot-filling, Intent classification, and Virtual assistant Evaluation. MASSIVE contains 1M realistic, parallel, labeled virtual assistant utterances spanning 51 languages, 18 domains, 60 intents, and 55 slots. MASSIVE was created by tasking professional translators to localize the English-only SLURP dataset into 50 typologically diverse languages from 29 genera. We also present modeling results on XLM-R and mT5, including exact match accuracy, intent classification accuracy, and slot-filling F1 score. We have released our dataset, modeling code, and models publicly.

Jack FitzGerald, Shankar Ananthakrishnan, Konstantine Arkoudas et al. · amazon-science, gatech

We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system. Though we train using 70% spoken-form data, our teacher models perform comparably to XLM-R and mT5 when evaluated on the written-form Cross-lingual Natural Language Inference (XNLI) corpus. We perform a second stage of pretraining on our teacher models using in-domain data from our system, improving error rates by 3.86% relative for intent classification and 7.01% relative for slot filling. We find that even a 170M-parameter model distilled from our Stage 2 teacher model has 2.88% better intent classification and 7.69% better slot filling error rates when compared to the 2.3B-parameter teacher trained only on public data (Stage 1), emphasizing the importance of in-domain data for pretraining. When evaluated offline using labeled NLU data, our 17M-parameter Stage 2 distilled model outperforms both XLM-R Base (85M params) and DistillBERT (42M params) by 4.23% to 6.14%, respectively. Finally, we present results from a full virtual assistant experimentation platform, where we find that models trained using our pretraining and distillation pipeline outperform models distilled from 85M-parameter teachers by 3.74%-4.91% on an automatic measurement of full-system user dissatisfaction.

Saleh Soltan, Shankar Ananthakrishnan, Jack FitzGerald et al. · amazon-science, gatech

In this work, we demonstrate that multilingual large-scale sequence-to-sequence (seq2seq) models, pre-trained on a mixture of denoising and Causal Language Modeling (CLM) tasks, are more efficient few-shot learners than decoder-only models on various tasks. In particular, we train a 20 billion parameter multilingual seq2seq model called Alexa Teacher Model (AlexaTM 20B) and show that it achieves state-of-the-art (SOTA) performance on 1-shot summarization tasks, outperforming a much larger 540B PaLM decoder model. AlexaTM 20B also achieves SOTA in 1-shot machine translation, especially for low-resource languages, across almost all language pairs supported by the model (Arabic, English, French, German, Hindi, Italian, Japanese, Marathi, Portuguese, Spanish, Tamil, and Telugu) on Flores-101 dataset. We also show in zero-shot setting, AlexaTM 20B outperforms GPT3 (175B) on SuperGLUE and SQuADv2 datasets and provides SOTA performance on multilingual tasks such as XNLI, XCOPA, Paws-X, and XWinograd. Overall, our results present a compelling case for seq2seq models as a powerful alternative to decoder-only models for Large-scale Language Model (LLM) training.

Yi-Jyun Sun, Suvodip Dey, Dilek Hakkani-Tur et al.

Estimation of a model's confidence on its outputs is critical for Conversational AI systems based on large language models (LLMs), especially for reducing hallucination and preventing over-reliance. In this work, we provide an exhaustive exploration of methods, including approaches proposed for open- and closed-weight LLMs, aimed at quantifying and leveraging model uncertainty to improve the reliability of LLM-generated responses, specifically focusing on dialogue state tracking (DST) in task-oriented dialogue systems (TODS). Regardless of the model type, well-calibrated confidence scores are essential to handle uncertainties, thereby improving model performance. We evaluate four methods for estimating confidence scores based on softmax, raw token scores, verbalized confidences, and a combination of these methods, using the area under the curve (AUC) metric to assess calibration, with higher AUC indicating better calibration. We also enhance these with a self-probing mechanism, proposed for closed models. Furthermore, we assess these methods using an open-weight model fine-tuned for the task of DST, achieving superior joint goal accuracy (JGA). Our findings also suggest that fine-tuning open-weight LLMs can result in enhanced AUC performance, indicating better confidence score calibration.

Stuti Agrawal, Nishi Uppuluri, Pranav Pillai et al.

LLM-driven dialog systems are used in a diverse set of applications, ranging from healthcare to customer service. However, given their generalization capability, it is difficult to ensure that these chatbots stay within the boundaries of the specialized domains, potentially resulting in inaccurate information and irrelevant responses. This paper introduces an unsupervised approach for automatically inducing domain-specific dialog flows that can be used to constrain LLM-based chatbots. We introduce two variants of dialog flow based on the availability of in-domain conversation instances. Through human and automatic evaluation over various dialog domains, we demonstrate that our high-quality data-guided dialog flows achieve better domain coverage, thereby overcoming the need for extensive manual crafting of such flows.

Emre Can Acikgoz, Jinoh Oh, Jie Hao et al.

Effective human-agent collaboration is increasingly prevalent in real-world applications. Current trends in such collaborations are predominantly unidirectional, with users providing instructions or posing questions to agents, where agents respond directly without seeking necessary clarifications or confirmations. However, the evolving capabilities of these agents require more proactive engagement, where agents should dynamically participate in conversations to clarify user intents, resolve ambiguities, and adapt to changing circumstances. Existing prior work under-utilize the conversational capabilities of language models (LMs), thereby optimizing agents as better followers rather than effective speakers. In this work, we introduce SpeakRL, a reinforcement learning (RL) method that enhances agents' conversational capabilities by rewarding proactive interactions with users, such as asking right clarification questions when necessary. To support this, we curate SpeakER, a synthetic dataset that includes diverse scenarios from task-oriented dialogues, where tasks are resolved through interactive clarification questions. We present a systematic analysis of reward design for conversational proactivity and propose a principled reward formulation for teaching agents to balance asking with acting. Empirical evaluations demonstrate that our approach achieves a 20.14% absolute improvement in task completion over base models without increasing conversation turns even surpassing even much larger proprietary models, demonstrating the promise of clarification-centric user-agent interactions.

Emre Can Acikgoz, Jinoh Oh, Joo Hyuk Jeon et al.

Conversational agents often encounter ambiguous user requests, requiring an effective clarification to successfully complete tasks. While recent advancements in real-world applications favor multi-agent architectures to manage complex conversational scenarios efficiently, ambiguity resolution remains a critical and underexplored challenge--particularly due to the difficulty of determining which agent should initiate a clarification and how agents should coordinate their actions when faced with uncertain or incomplete user input. The fundamental questions of when to interrupt a user and how to formulate the optimal clarification query within the most optimal multi-agent settings remain open. In this paper, we propose MAC (Multi-Agent Clarification), an interactive multi-agent framework specifically optimized to resolve user ambiguities by strategically managing clarification dialogues. We first introduce a novel taxonomy categorizing user ambiguities to systematically guide clarification strategies. Then, we present MAC that autonomously coordinates multiple agents to interact synergistically with users. Empirical evaluations on MultiWOZ 2.4 demonstrate that enabling clarification at both levels increases task success rate 7.8\% (54.5 to 62.3) and reduces the average number of dialogue turns (6.53 to 4.86) by eliciting all required user information up front and minimizing repetition. Our findings highlight the importance of active user interaction and role-aware clarification for more reliable human-agent communication.

Takyoung Kim, Jinseok Nam, Chandrayee Basu et al.

Conversational agents powered by large language models (LLMs) with tool integration achieve strong performance on fixed task-oriented dialogue datasets but remain vulnerable to unanticipated, user-induced errors. Rather than focusing on error prevention, this work focuses on error recovery, which necessitates the accurate diagnosis of erroneous dialogue contexts and execution of proper recovery plans. Under realistic constraints precluding model fine-tuning or prompt modification due to significant cost and time requirements, we explore whether agents can recover from contextually flawed interactions and how their behavior can be adapted without altering model parameters and prompts. To this end, we propose Reasoning Inception (ReIn), a test-time intervention method that plants an initial reasoning into the agent's decision-making process. Specifically, an external inception module identifies predefined errors within the dialogue context and generates recovery plans, which are subsequently integrated into the agent's internal reasoning process to guide corrective actions, without modifying its parameters or system prompts. We evaluate ReIn by systematically simulating conversational failure scenarios that directly hinder successful completion of user goals: user's ambiguous and unsupported requests. Across diverse combinations of agent models and inception modules, ReIn substantially improves task success and generalizes to unseen error types. Moreover, it consistently outperforms explicit prompt-modification approaches, underscoring its utility as an efficient, on-the-fly method. In-depth analysis of its operational mechanism, particularly in relation to instruction hierarchy, indicates that jointly defining recovery tools with ReIn can serve as a safe and effective strategy for improving the resilience of conversational agents without modifying the backbone models or system prompts.

Cheng Qian, Emre Can Acikgoz, Bingxuan Li et al.

Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer a promising remedy: agents could use them as external simulators to foresee outcomes before acting. This paper empirically examines whether current agents can leverage such world models as tools to enhance their cognition. Across diverse agentic and visual question answering tasks, we observe that some agents rarely invoke simulation (fewer than 1%), frequently misuse predicted rollouts (approximately 15%), and often exhibit inconsistent or even degraded performance (up to 5%) when simulation is available or enforced. Attribution analysis further indicates that the primary bottleneck lies in the agents' capacity to decide when to simulate, how to interpret predicted outcomes, and how to integrate foresight into downstream reasoning. These findings underscore the need for mechanisms that foster calibrated, strategic interaction with world models, paving the way toward more reliable anticipatory cognition in future agent systems.

Sumuk Shashidhar, Clémentine Fourrier, Alina Lozovskia et al.

Evaluating large language models (LLMs) effectively remains a critical bottleneck, as traditional static benchmarks suffer from saturation and contamination, while human evaluations are costly and slow. This hinders timely or domain-specific assessment, crucial for real-world applications. We introduce YourBench, a novel, open-source framework that addresses these limitations by enabling dynamic, automated generation of reliable, up-to-date, and domain-tailored benchmarks cheaply and without manual annotation, directly from user-provided documents. We demonstrate its efficacy by replicating 7 diverse MMLU subsets using minimal source text, achieving this for under 15 USD in total inference costs while perfectly preserving the relative model performance rankings (Spearman Rho = 1) observed on the original benchmark. To ensure that YourBench generates data grounded in provided input instead of relying on posterior parametric knowledge in models, we also introduce Tempora-0325, a novel dataset of over 7K diverse documents, published exclusively after March 2025. Our comprehensive analysis spans 26 SoTA models from 7 major families across varying scales (3-671B parameters) to validate the quality of generated evaluations through rigorous algorithmic checks (e.g., citation grounding) and human assessments. We release the YourBench library, the Tempora-0325 dataset, 150k+ question answer pairs based on Tempora and all evaluation and inference traces to facilitate reproducible research and empower the community to generate bespoke benchmarks on demand, fostering more relevant and trustworthy LLM evaluation.

Emre Can Acikgoz, Cheng Qian, Hongru Wang et al.

Recent advances in Large Language Models (LLMs) have propelled conversational AI from traditional dialogue systems into sophisticated agents capable of autonomous actions, contextual awareness, and multi-turn interactions with users. Yet, fundamental questions about their capabilities, limitations, and paths forward remain open. This survey paper presents a desideratum for next-generation Conversational Agents - what has been achieved, what challenges persist, and what must be done for more scalable systems that approach human-level intelligence. To that end, we systematically analyze LLM-driven Conversational Agents by organizing their capabilities into three primary dimensions: (i) Reasoning - logical, systematic thinking inspired by human intelligence for decision making, (ii) Monitor - encompassing self-awareness and user interaction monitoring, and (iii) Control - focusing on tool utilization and policy following. Building upon this, we introduce a novel taxonomy by classifying recent work on Conversational Agents around our proposed desideratum. We identify critical research gaps and outline key directions, including realistic evaluations, long-term multi-turn reasoning skills, self-evolution capabilities, collaborative and multi-agent task completion, personalization, and proactivity. This work aims to provide a structured foundation, highlight existing limitations, and offer insights into potential future research directions for Conversational Agents, ultimately advancing progress toward Artificial General Intelligence (AGI). We maintain a curated repository of papers at: https://github.com/emrecanacikgoz/awesome-conversational-agents.

Emre Can Acikgoz, Cheng Qian, Jonas Hübotter et al.

Large language models (LLMs) are becoming the foundation for autonomous agents that can use tools to solve complex tasks. Reinforcement learning (RL) has emerged as a common approach for injecting such agentic capabilities, but typically under tightly controlled training setups. It often depends on carefully constructed task-solution pairs and substantial human supervision, which creates a fundamental obstacle to open-ended self-evolution toward superintelligent systems. In this paper, we propose Tool-R0 framework for training general purpose tool-calling agents from scratch with self-play RL, under a zero-data assumption. Initialized from the same base LLM, Tool-R0 co-evolves a Generator and a Solver with complementary rewards: one proposes targeted challenging tasks at the other's competence frontier and the other learns to solve them with real-world tool calls. This creates a self-evolving cycle that requires no pre-existing tasks or datasets. Evaluation on different tool-use benchmarks show that Tool-R0 yields 92.5 relative improvement over the base model and surpasses fully supervised tool-calling baselines under the same setting. Our work further provides empirical insights into self-play LLM agents by analyzing co-evolution, curriculum dynamics, and scaling behavior.

Cheng Qian, Emre Can Acikgoz, Qi He et al.

Current Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities. However, SFT struggles to generalize to unfamiliar or complex tool use scenarios. Recent advancements in reinforcement learning (RL), particularly with R1-like models, have demonstrated promising reasoning and generalization abilities. Yet, reward design for tool use presents unique challenges: multiple tools may be invoked with diverse parameters, and coarse-grained reward signals, such as answer matching, fail to offer the finegrained feedback required for effective learning. In this work, we present the first comprehensive study on reward design for tool selection and application tasks within the RL paradigm. We systematically explore a wide range of reward strategies, analyzing their types, scales, granularity, and temporal dynamics. Building on these insights, we propose a principled reward design tailored for tool use tasks and apply it to train LLMs using Group Relative Policy Optimization (GRPO). Empirical evaluations across diverse benchmarks demonstrate that our approach yields robust, scalable, and stable training, achieving a 17% improvement over base models and a 15% gain over SFT models. These results highlight the critical role of thoughtful reward design in enhancing the tool use capabilities and generalization performance of LLMs. All the codes are released to facilitate future research.

Lei Shu, Piero Molino, Mahdi Namazifar et al.

This paper proposes a novel end-to-end architecture for task-oriented dialogue systems. It is based on a simple and practical yet very effective sequence-to-sequence approach, where language understanding and state tracking tasks are modeled jointly with a structured copy-augmented sequential decoder and a multi-label decoder for each slot. The policy engine and language generation tasks are modeled jointly following that. The copy-augmented sequential decoder deals with new or unknown values in the conversation, while the multi-label decoder combined with the sequential decoder ensures the explicit assignment of values to slots. On the generation part, slot binary classifiers are used to improve performance. This architecture is scalable to real-world scenarios and is shown through an empirical evaluation to achieve state-of-the-art performance on both the Cambridge Restaurant dataset and the Stanford in-car assistant dataset\footnote{The code is available at \url{https://github.com/uber-research/FSDM}}

Cheng Qian, Emre Can Acikgoz, Hongru Wang et al.

Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness, failing to balance these approaches effectively. This imbalance leads to Tool Overuse, where models unnecessarily rely on external tools for tasks solvable with parametric knowledge, increasing computational overhead. Inspired by human metacognition, we introduce SMART (Strategic Model-Aware Reasoning with Tools), a paradigm that enhances an agent's self-awareness to optimize task handling and reduce tool overuse. To support this paradigm, we introduce SMART-ER, a dataset spanning three domains, where reasoning alternates between parametric knowledge and tool-dependent steps, with each step enriched by rationales explaining when tools are necessary. Through supervised training, we develop SMARTAgent, a family of models that dynamically balance parametric knowledge and tool use. Evaluations show that SMARTAgent reduces tool use by 24% while improving performance by over 37%, enabling 7B-scale models to match its 70B counterpart and GPT-4o. Additionally, SMARTAgent generalizes to out-of-distribution test data like GSM8K and MINTQA, maintaining accuracy with just one-fifth the tool calls. These highlight the potential of strategic tool use to enhance reasoning, mitigate overuse, and bridge the gap between model size and performance, advancing intelligent and resource-efficient agent designs.

Emre Can Acikgoz, Jeremiah Greer, Akul Datta et al.

Large Language Models (LLMs) with API-calling capabilities enabled building effective Language Agents (LA), while also revolutionizing the conventional task-oriented dialogue (TOD) paradigm. However, current approaches face a critical dilemma: TOD systems are often trained on a limited set of target APIs, requiring new data to maintain their quality when interfacing with new services, while LAs are not trained to maintain user intent over multi-turn conversations. Because both robust multi-turn management and advanced function calling are crucial for effective conversational agents, we evaluate these skills on three popular benchmarks: MultiWOZ 2.4 (TOD), BFCL V3 (LA), and API-Bank (LA), and our analyses reveal that specialized approaches excel in one domain but underperform in the other. To bridge this chasm, we introduce CoALM (Conversational Agentic Language Model), a unified approach that integrates both conversational and agentic capabilities. We created CoALM-IT, a carefully constructed multi-task dataset that interleave multi-turn ReAct reasoning with complex API usage. Using CoALM-IT, we train three models CoALM 8B, CoALM 70B, and CoALM 405B, which outperform top domain-specific models, including GPT-4o, across all three benchmarks. This demonstrates the feasibility of a single model approach for both TOD and LA, setting a new standard for conversational agents.

Nimet Beyza Bozdag, Shuhaib Mehri, Gokhan Tur et al.

Large Language Models (LLMs) demonstrate persuasive capabilities that rival human-level persuasion. While these capabilities can be used for social good, they also present risks of potential misuse. Moreover, LLMs' susceptibility to persuasion raises concerns about alignment with ethical principles. To study these dynamics, we introduce Persuade Me If You Can (PMIYC), an automated framework for evaluating persuasion through multi-agent interactions. Here, Persuader agents engage in multi-turn conversations with the Persuadee agents, allowing us to measure LLMs' persuasive effectiveness and their susceptibility to persuasion. We conduct comprehensive evaluations across diverse LLMs, ensuring each model is assessed against others in both subjective and misinformation contexts. We validate the efficacy of our framework through human evaluations and show alignment with prior work. PMIYC offers a scalable alternative to human annotation for studying persuasion in LLMs. Through PMIYC, we find that Llama-3.3-70B and GPT-4o exhibit similar persuasive effectiveness, outperforming Claude 3 Haiku by 30%. However, GPT-4o demonstrates over 50% greater resistance to persuasion for misinformation compared to Llama-3.3-70B. These findings provide empirical insights into the persuasive dynamics of LLMs and contribute to the development of safer AI systems.

Vardhan Dongre, Xiaocheng Yang, Emre Can Acikgoz et al.

Large language model (LLM)-based agents are increasingly employed to interact with external environments (e.g., games, APIs, world models) to solve user-provided tasks. However, current frameworks often lack the ability to collaborate effectively with users in fully conversational settings. Conversations are essential for aligning on task details, achieving user-defined goals, and satisfying preferences. While existing agents address ambiguity through clarification questions, they underutilize the broader potential of an LLM's conversational capabilities. In this work, we introduce ReSpAct, an LLM-based agent designed to seamlessly integrate reasoning, decision-making, and dynamic dialogue for task-solving. Expanding on reasoning-first approaches like ReAct, ReSpAct employs active, free-flowing dialogues to interpret instructions, clarify goals, provide status updates, resolve subtask failures, and refine plans based on user inputs without any explicit dialogue schema. By alternating between task-solving actions and interactive conversations, ReSpAct demonstrates improved performance across diverse environments. We evaluate ReSpAct in user-interactive settings, including task-oriented dialogue systems (MultiWOZ) and decision-making tasks (ALFWorld, WebShop). ReSpAct outperforms ReAct with absolute success rate improvements of 6% and 4% in ALFWorld and WebShop, respectively, and achieves a 5.5% gain in Inform and a 3% gain in Success scores in MultiWOZ. These results highlight the value of integrating dynamic user-agent collaboration for more effective task resolution.

Nimet Beyza Bozdag, Shuhaib Mehri, Xiaocheng Yang et al.

Persuasion is a fundamental aspect of communication, influencing decision-making across diverse contexts, from everyday conversations to high-stakes scenarios such as politics, marketing, and law. The rise of conversational AI systems has significantly expanded the scope of persuasion, introducing both opportunities and risks. AI-driven persuasion can be leveraged for beneficial applications, but also poses threats through manipulation and unethical influence. Moreover, AI systems are not only persuaders, but also susceptible to persuasion, making them vulnerable to adversarial attacks and bias reinforcement. Despite rapid advancements in AI-generated persuasive content, our understanding of what makes persuasion effective remains limited due to its inherently subjective and context-dependent nature. In this survey, we provide a comprehensive overview of computational persuasion, structured around three key perspectives: (1) AI as a Persuader, which explores AI-generated persuasive content and its applications; (2) AI as a Persuadee, which examines AI's susceptibility to influence and manipulation; and (3) AI as a Persuasion Judge, which analyzes AI's role in evaluating persuasive strategies, detecting manipulation, and ensuring ethical persuasion. We introduce a taxonomy for computational persuasion research and discuss key challenges, including evaluating persuasiveness, mitigating manipulative persuasion, and developing responsible AI-driven persuasive systems. Our survey outlines future research directions to enhance the safety, fairness, and effectiveness of AI-powered persuasion while addressing the risks posed by increasingly capable language models.

Taaha Kazi, Ruiliang Lyu, Sizhe Zhou et al.

Traditionally, offline datasets have been used to evaluate task-oriented dialogue (TOD) models. These datasets lack context awareness, making them suboptimal benchmarks for conversational systems. In contrast, user-agents, which are context-aware, can simulate the variability and unpredictability of human conversations, making them better alternatives as evaluators. Prior research has utilized large language models (LLMs) to develop user-agents. Our work builds upon this by using LLMs to create user-agents for the evaluation of TOD systems. This involves prompting an LLM, using in-context examples as guidance, and tracking the user-goal state. Our evaluation of diversity and task completion metrics for the user-agents shows improved performance with the use of better prompts. Additionally, we propose methodologies for the automatic evaluation of TOD models within this dynamic framework.

Daniel Philipov, Vardhan Dongre, Gokhan Tur et al.

Embodied agents designed to assist users with tasks must engage in natural language interactions, interpret instructions, execute actions, and communicate effectively to resolve issues. However, collecting large-scale, diverse datasets of situated human-robot dialogues to train and evaluate such agents is expensive, labor-intensive, and time-consuming. To address this challenge, we propose building a large language model (LLM)-based user agent that can simulate user behavior during interactions with an embodied agent in a virtual environment. Given a user goal (e.g., make breakfast), at each time step, the user agent may observe" the robot actions or speak" to either intervene with the robot or answer questions. Such a user agent assists in improving the scalability and efficiency of embodied dialogues dataset generation and is critical for enhancing and evaluating the robot's interaction and task completion ability, as well as for research in reinforcement learning using AI feedback. We evaluate our user agent's ability to generate human-like behaviors by comparing its simulated dialogues with the TEACh dataset. We perform three experiments: zero-shot prompting to predict dialogue acts, few-shot prompting, and fine-tuning on the TEACh training subset. Results show the LLM-based user agent achieves an F-measure of 42% with zero-shot prompting and 43.4% with few-shot prompting in mimicking human speaking behavior. Through fine-tuning, performance in deciding when to speak remained stable, while deciding what to say improved from 51.1% to 62.5%. These findings showcase the feasibility of the proposed approach for assessing and enhancing the effectiveness of robot task completion through natural language communication.

Shuhaib Mehri, Xiaocheng Yang, Takyoung Kim et al.

User simulators are essential to conversational AI, enabling scalable agent development and evaluation through simulated interactions. While current Large Language Models (LLMs) have advanced user simulation capabilities, we reveal that they struggle to consistently demonstrate goal-oriented behavior across multi-turn conversations--a critical limitation that compromises their reliability in downstream applications. We introduce User Goal State Tracking (UGST), a novel framework that tracks user goal progression throughout conversations. Leveraging UGST, we present a three-stage methodology for developing user simulators that can autonomously track goal progression and reason to generate goal-aligned responses. Moreover, we establish comprehensive evaluation metrics for measuring goal alignment in user simulators, and demonstrate that our approach yields substantial improvements across two benchmarks (MultiWOZ 2.4 and τ-Bench). Our contributions address a critical gap in conversational AI and establish UGST as an essential framework for developing goal-aligned user simulators.

Emre Can Acikgoz, Carl Guo, Suvodip Dey et al.

Task-oriented dialogue (TOD) systems are experiencing a revolution driven by Large Language Models (LLMs), yet the evaluation methodologies for these systems remain insufficient for their growing sophistication. While traditional automatic metrics effectively assessed earlier modular systems, they focus solely on the dialogue level and cannot detect critical intermediate errors that can arise during user-agent interactions. In this paper, we introduce TD-EVAL (Turn and Dialogue-level Evaluation), a two-step evaluation framework that unifies fine-grained turn-level analysis with holistic dialogue-level comparisons. At turn level, we evaluate each response along three TOD-specific dimensions: conversation cohesion, backend knowledge consistency, and policy compliance. Meanwhile, we design TOD Agent Arena that uses pairwise comparisons to provide a measure of dialogue-level quality. Through experiments on MultiWOZ 2.4 and τ-Bench, we demonstrate that TD-EVAL effectively identifies the conversational errors that conventional metrics miss. Furthermore, TD-EVAL exhibits better alignment with human judgments than traditional and LLM-based metrics. These findings demonstrate that TD-EVAL introduces a new paradigm for TOD system evaluation, efficiently assessing both turn and system levels with a plug-and-play framework for future research.

Takyoung Kim, Janvijay Singh, Shuhaib Mehri et al.

The growing capabilities of large language models (LLMs) in instruction-following and context-understanding lead to the era of agents with numerous applications. Among these, task planning agents have become especially prominent in realistic scenarios involving complex internal pipelines, such as context understanding, tool management, and response generation. However, existing benchmarks predominantly evaluate agent performance based on task completion as a proxy for overall effectiveness. We hypothesize that merely improving task completion is misaligned with maximizing user satisfaction, as users interact with the entire agentic process and not only the end result. To address this gap, we propose PIPA, a unified evaluation protocol that conceptualizes the behavioral process of interactive task planning agents within a partially observable Markov Decision Process (POMDP) paradigm. The proposed protocol offers a comprehensive assessment of agent performance through a set of atomic evaluation criteria, allowing researchers and practitioners to diagnose specific strengths and weaknesses within the agent's decision-making pipeline. Our analyses show that agents excel in different behavioral stages, with user satisfaction shaped by both outcomes and intermediate behaviors. We also highlight future directions, including systems that leverage multiple agents and the limitations of user simulators in task planning.

Ananth Hariharan, Vardhan Dongre, Dilek Hakkani-Tür et al.

Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors that reduce policy quality. We propose an iterative verification framework in which a Judge LLM critiques action sequences and a Planner LLM applies the revisions, yielding progressively cleaner and more spatially coherent trajectories. Unlike rule-based approaches, our method relies on natural language prompting, enabling broad generalization across error types including irrelevant actions, contradictions, and missing steps. On a set of manually annotated actions from the TEACh embodied AI dataset, our framework achieves up to 90% recall and 100% precision across four state-of-the-art LLMs (GPT o4-mini, DeepSeek-R1, Gemini 2.5, LLaMA 4 Scout). The refinement loop converges quickly, with 96.5% of sequences requiring at most three iterations, while improving both temporal efficiency and spatial action organization. Crucially, the method preserves human error-recovery patterns rather than collapsing them, supporting future work on robust corrective behavior. By establishing plan verification as a reliable LLM capability for spatial planning and action refinement, we provide a scalable path to higher-quality training data for imitation learning in embodied AI.

Emre Can Acikgoz, Cheng Qian, Heng Ji et al.

One paradigm of language model (LM) fine-tuning relies on creating large training datasets, under the assumption that high quantity and diversity will enable models to generalize to novel tasks after post-training. In practice, gathering large sets of data is inefficient, and training on them is prohibitively expensive; worse, there is no guarantee that the resulting model will handle complex scenarios or generalize better. Moreover, existing techniques rarely assess whether a training sample provides novel information or is redundant with the knowledge already acquired by the model, resulting in unnecessary costs. In this work, we explore a new test-time self-improvement method to create more effective and generalizable agentic LMs on-the-fly. The proposed algorithm can be summarized in three steps: (i) first it identifies the samples that model struggles with (self-awareness), (ii) then generates similar examples from detected uncertain samples (self-data augmentation), and (iii) uses these newly generated samples at test-time fine-tuning (self-improvement). We study two variants of this approach: Test-Time Self-Improvement (TT-SI), where the same model generates additional training examples from its own uncertain cases and then learns from them, and contrast this approach with Test-Time Distillation (TT-D), where a stronger model generates similar examples for uncertain cases, enabling student to adapt using distilled supervision. Empirical evaluations across different agent benchmarks demonstrate that TT-SI improves the performance with +5.48% absolute accuracy gain on average across all benchmarks and surpasses other standard learning methods, yet using 68x less training samples. Our findings highlight the promise of TT-SI, demonstrating the potential of self-improvement algorithms at test-time as a new paradigm for building more capable agents toward self-evolution.

Vardhan Dongre, Chi Gui, Shubham Garg et al.

We introduce MIRAGE, a new benchmark for multimodal expert-level reasoning and decision-making in consultative interaction settings. Designed for the agriculture domain, MIRAGE captures the full complexity of expert consultations by combining natural user queries, expert-authored responses, and image-based context, offering a high-fidelity benchmark for evaluating models on grounded reasoning, clarification strategies, and long-form generation in a real-world, knowledge-intensive domain. Grounded in over 35,000 real user-expert interactions and curated through a carefully designed multi-step pipeline, MIRAGE spans diverse crop health, pest diagnosis, and crop management scenarios. The benchmark includes more than 7,000 unique biological entities, covering plant species, pests, and diseases, making it one of the most taxonomically diverse benchmarks available for vision-language models, grounded in the real world. Unlike existing benchmarks that rely on well-specified user inputs and closed-set taxonomies, MIRAGE features underspecified, context-rich scenarios with open-world settings, requiring models to infer latent knowledge gaps, handle rare entities, and either proactively guide the interaction or respond. Project Page: https://mirage-benchmark.github.io

Suvodip Dey, Yi-Jyun Sun, Gokhan Tur et al.

Recent LLMs have enabled significant advancements for conversational agents. However, they are also well known to hallucinate, producing responses that seem plausible but are factually incorrect. On the other hand, users tend to over-rely on LLM-based AI agents, accepting AI's suggestion even when it is wrong. Adding positive friction, such as explanations or getting user confirmations, has been proposed as a mitigation in AI-supported decision-making systems. In this paper, we propose an accountability model for LLM-based task-oriented dialogue agents to address user overreliance via friction turns in cases of model uncertainty and errors associated with dialogue state tracking (DST). The accountability model is an augmented LLM with an additional accountability head that functions as a binary classifier to predict the relevant slots of the dialogue state mentioned in the conversation. We perform our experiments with multiple backbone LLMs on two established benchmarks (MultiWOZ and Snips). Our empirical findings demonstrate that the proposed approach not only enables reliable estimation of AI agent errors but also guides the decoder in generating more accurate actions. We observe around 3% absolute improvement in joint goal accuracy (JGA) of DST output by incorporating accountability heads into modern LLMs. Self-correcting the detected errors further increases the JGA from 67.13 to 70.51, achieving state-of-the-art DST performance. Finally, we show that error correction through user confirmations (friction turn) achieves a similar performance gain, highlighting its potential to reduce user overreliance.

Aishwarya Padmakumar, Jesse Thomason, Ayush Shrivastava et al.

Robots operating in human spaces must be able to engage in natural language interaction with people, both understanding and executing instructions, and using conversation to resolve ambiguity and recover from mistakes. To study this, we introduce TEACh, a dataset of over 3,000 human--human, interactive dialogues to complete household tasks in simulation. A Commander with access to oracle information about a task communicates in natural language with a Follower. The Follower navigates through and interacts with the environment to complete tasks varying in complexity from "Make Coffee" to "Prepare Breakfast", asking questions and getting additional information from the Commander. We propose three benchmarks using TEACh to study embodied intelligence challenges, and we evaluate initial models' abilities in dialogue understanding, language grounding, and task execution.

Alexandros Papangelis, Karthik Gopalakrishnan, Aishwarya Padmakumar et al.

Inspired by recent work in meta-learning and generative teaching networks, we propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data (given some seed data) and then train themselves from that data to perform a given task. We use reinforcement learning to optimize the data generation process where the reward signal is the agent's performance on the task. The task can be any language-related task, from intent detection to full task-oriented conversations. In this work, we show that our approach is able to generalise from seed data and performs well in limited data and limited computation settings, with significant gains for intent detection and slot tagging across multiple datasets: ATIS, TOD, SNIPS, and Restaurants8k. We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data. We also conduct an analysis of the novelty of the generated data and provide generated examples for intent detection, slot tagging, and non-goal oriented conversations.

Tao Tu, Qing Ping, Govind Thattai et al.

GuessWhat?! is a two-player visual dialog guessing game where player A asks a sequence of yes/no questions (Questioner) and makes a final guess (Guesser) about a target object in an image, based on answers from player B (Oracle). Based on this dialog history between the Questioner and the Oracle, a Guesser makes a final guess of the target object. Previous baseline Oracle model encodes no visual information in the model, and it cannot fully understand complex questions about color, shape, relationships and so on. Most existing work for Guesser encode the dialog history as a whole and train the Guesser models from scratch on the GuessWhat?! dataset. This is problematic since language encoder tend to forget long-term history and the GuessWhat?! data is sparse in terms of learning visual grounding of objects. Previous work for Questioner introduces state tracking mechanism into the model, but it is learned as a soft intermediates without any prior vision-linguistic insights. To bridge these gaps, in this paper we propose Vilbert-based Oracle, Guesser and Questioner, which are all built on top of pretrained vision-linguistic model, Vilbert. We introduce two-way background/target fusion mechanism into Vilbert-Oracle to account for both intra and inter-object questions. We propose a unified framework for Vilbert-Guesser and Vilbert-Questioner, where state-estimator is introduced to best utilize Vilbert's power on single-turn referring expression comprehension. Experimental results show that our proposed models outperform state-of-the-art models significantly by 7%, 10%, 12% for Oracle, Guesser and End-to-End Questioner respectively.

Mahdi Namazifar, John Malik, Li Erran Li et al.

Masked language models have revolutionized natural language processing systems in the past few years. A recently introduced generalization of masked language models called warped language models are trained to be more robust to the types of errors that appear in automatic or manual transcriptions of spoken language by exposing the language model to the same types of errors during training. In this work we propose a novel approach that takes advantage of the robustness of warped language models to transcription noise for correcting transcriptions of spoken language. We show that our proposed approach is able to achieve up to 10% reduction in word error rates of both automatic and manual transcriptions of spoken language.

Shane Storks, Qiaozi Gao, Govind Thattai et al.

Embodied instruction following is a challenging problem requiring an agent to infer a sequence of primitive actions to achieve a goal environment state from complex language and visual inputs. Action Learning From Realistic Environments and Directives (ALFRED) is a recently proposed benchmark for this problem consisting of step-by-step natural language instructions to achieve subgoals which compose to an ultimate high-level goal. Key challenges for this task include localizing target locations and navigating to them through visual inputs, and grounding language instructions to visual appearance of objects. To address these challenges, in this study, we augment the agent's field of view during navigation subgoals with multiple viewing angles, and train the agent to predict its relative spatial relation to the target location at each timestep. We also improve language grounding by introducing a pre-trained object detection module to the model pipeline. Empirical studies show that our approach exceeds the baseline model performance.

Yi-Chia Wang, Alexandros Papangelis, Runze Wang et al.

Goal-oriented conversational agents are becoming prevalent in our daily lives. For these systems to engage users and achieve their goals, they need to exhibit appropriate social behavior as well as provide informative replies that guide users through tasks. The first component of the research in this paper applies statistical modeling techniques to understand conversations between users and human agents for customer service. Analyses show that social language used by human agents is associated with greater users' responsiveness and task completion. The second component of the research is the construction of a conversational agent model capable of injecting social language into an agent's responses while still preserving content. The model uses a sequence-to-sequence deep learning architecture, extended with a social language understanding element. Evaluation in terms of content preservation and social language level using both human judgment and automatic linguistic measures shows that the model can generate responses that enable agents to address users' issues in a more socially appropriate way.

Qing Ping, Feiyang Niu, Govind Thattai et al.

Current conversational AI systems aim to understand a set of pre-designed requests and execute related actions, which limits them to evolve naturally and adapt based on human interactions. Motivated by how children learn their first language interacting with adults, this paper describes a new Teachable AI system that is capable of learning new language nuggets called concepts, directly from end users using live interactive teaching sessions. The proposed setup uses three models to: a) Identify gaps in understanding automatically during live conversational interactions, b) Learn the respective interpretations of such unknown concepts from live interactions with users, and c) Manage a classroom sub-dialogue specifically tailored for interactive teaching sessions. We propose state-of-the-art transformer based neural architectures of models, fine-tuned on top of pre-trained models, and show accuracy improvements on the respective components. We demonstrate that this method is very promising in leading way to build more adaptive and personalized language understanding models.

Weixin Liang, Feiyang Niu, Aishwarya Reganti et al.

The predominant approach to visual question answering (VQA) relies on encoding the image and question with a "black-box" neural encoder and decoding a single token as the answer like "yes" or "no". Despite this approach's strong quantitative results, it struggles to come up with intuitive, human-readable forms of justification for the prediction process. To address this insufficiency, we reformulate VQA as a full answer generation task, which requires the model to justify its predictions in natural language. We propose LRTA [Look, Read, Think, Answer], a transparent neural-symbolic reasoning framework for visual question answering that solves the problem step-by-step like humans and provides human-readable form of justification at each step. Specifically, LRTA learns to first convert an image into a scene graph and parse a question into multiple reasoning instructions. It then executes the reasoning instructions one at a time by traversing the scene graph using a recurrent neural-symbolic execution module. Finally, it generates a full answer to the given question with natural language justifications. Our experiments on GQA dataset show that LRTA outperforms the state-of-the-art model by a large margin (43.1% v.s. 28.0%) on the full answer generation task. We also create a perturbed GQA test set by removing linguistic cues (attributes and relations) in the questions for analyzing whether a model is having a smart guess with superficial data correlations. We show that LRTA makes a step towards truly understanding the question while the state-of-the-art model tends to learn superficial correlations from the training data.

Mahdi Namazifar, Alexandros Papangelis, Gokhan Tur et al.

Different flavors of transfer learning have shown tremendous impact in advancing research and applications of machine learning. In this work we study the use of a specific family of transfer learning, where the target domain is mapped to the source domain. Specifically we map Natural Language Understanding (NLU) problems to QuestionAnswering (QA) problems and we show that in low data regimes this approach offers significant improvements compared to other approaches to NLU. Moreover we show that these gains could be increased through sequential transfer learning across NLU problems from different domains. We show that our approach could reduce the amount of required data for the same performance by up to a factor of 10.

Mahdi Namazifar, Gokhan Tur, Dilek Hakkani Tür

Masked Language Models (MLM) are self-supervised neural networks trained to fill in the blanks in a given sentence with masked tokens. Despite the tremendous success of MLMs for various text based tasks, they are not robust for spoken language understanding, especially for spontaneous conversational speech recognition noise. In this work we introduce Warped Language Models (WLM) in which input sentences at training time go through the same modifications as in MLM, plus two additional modifications, namely inserting and dropping random tokens. These two modifications extend and contract the sentence in addition to the modifications in MLMs, hence the word "warped" in the name. The insertion and drop modification of the input text during training of WLM resemble the types of noise due to Automatic Speech Recognition (ASR) errors, and as a result WLMs are likely to be more robust to ASR noise. Through computational results we show that natural language understanding systems built on top of WLMs perform better compared to those built based on MLMs, especially in the presence of ASR errors.

Lei Shu, Alexandros Papangelis, Yi-Chia Wang et al.

This work introduces Focused-Variation Network (FVN), a novel model to control language generation. The main problems in previous controlled language generation models range from the difficulty of generating text according to the given attributes, to the lack of diversity of the generated texts. FVN addresses these issues by learning disjoint discrete latent spaces for each attribute inside codebooks, which allows for both controllability and diversity, while at the same time generating fluent text. We evaluate FVN on two text generation datasets with annotated content and style, and show state-of-the-art performance as assessed by automatic and human evaluations.

Fei Tao, Gokhan Tur

Speaker verification is an established yet challenging task in speech processing and a very vibrant research area. Recent speaker verification (SV) systems rely on deep neural networks to extract high-level embeddings which are able to characterize the users' voices. Most of the studies have investigated on improving the discriminability of the networks to extract better embeddings for performances improvement. However, only few research focus on improving the generalization. In this paper, we propose to apply the ladder network framework in the SV systems, which combines the supervised and unsupervised learning fashions. The ladder network can make the system to have better high-level embedding by balancing the trade-off to keep/discard as much useful/useless information as possible. We evaluated the framework on two state-of-the-art SV systems, d-vector and x-vector, which can be used for different use cases. The experiments showed that the proposed approach relatively improved the performance by 10% at most without adding parameters and augmented data.

Patrick von Platen, Fei Tao, Gokhan Tur

Automatic speaker verification systems are vulnerable to audio replay attacks which bypass security by replaying recordings of authorized speakers. Replay attack detection (RA) detection systems built upon Residual Neural Networks (ResNet)s have yielded astonishing results on the public benchmark ASVspoof 2019 Physical Access challenge. With most teams using fine-tuned feature extraction pipelines and model architectures, the generalizability of such systems remains questionable though. In this work, we analyse the effect of discriminative feature learning in a multi-task learning (MTL) setting can have on the generalizability and discriminability of RA detection systems. We use a popular ResNet architecture optimized by the cross-entropy criterion as our baseline and compare it to the same architecture optimized by MTL using Siamese Neural Networks (SNN). It can be shown that SNN outperform the baseline by relative 26.8 % Equal Error Rate (EER). We further enhance the model's architecture and demonstrate that SNN with additional reconstruction loss yield another significant improvement of relative 13.8 % EER.

Yue Weng, Sai Sumanth Miryala, Chandra Khatri et al.

The quality of automatic speech recognition (ASR) is critical to Dialogue Systems as ASR errors propagate to and directly impact downstream tasks such as language understanding (LU). In this paper, we propose multi-task neural approaches to perform contextual language correction on ASR outputs jointly with LU to improve the performance of both tasks simultaneously. To measure the effectiveness of this approach we used a public benchmark, the 2nd Dialogue State Tracking (DSTC2) corpus. As a baseline approach, we trained task-specific Statistical Language Models (SLM) and fine-tuned state-of-the-art Generalized Pre-training (GPT) Language Model to re-rank the n-best ASR hypotheses, followed by a model to identify the dialog act and slots. i) We further trained ranker models using GPT and Hierarchical CNN-RNN models with discriminatory losses to detect the best output given n-best hypotheses. We extended these ranker models to first select the best ASR output and then identify the dialogue act and slots in an end to end fashion. ii) We also proposed a novel joint ASR error correction and LU model, a word confusion pointer network (WCN-Ptr) with multi-head self-attention on top, which consumes the word confusions populated from the n-best. We show that the error rates of off the shelf ASR and following LU systems can be reduced significantly by 14% relative with joint models trained using small amounts of in-domain data.

Andrea Madotto, Mahdi Namazifar, Joost Huizinga et al.

This work presents an exploration and imitation-learning-based agent capable of state-of-the-art performance in playing text-based computer games. Text-based computer games describe their world to the player through natural language and expect the player to interact with the game using text. These games are of interest as they can be seen as a testbed for language understanding, problem-solving, and language generation by artificial agents. Moreover, they provide a learning environment in which these skills can be acquired through interactions with an environment rather than using fixed corpora. One aspect that makes these games particularly challenging for learning agents is the combinatorially large action space. Existing methods for solving text-based games are limited to games that are either very simple or have an action space restricted to a predetermined set of admissible actions. In this work, we propose to use the exploration approach of Go-Explore for solving text-based games. More specifically, in an initial exploration phase, we first extract trajectories with high rewards, after which we train a policy to solve the game by imitating these trajectories. Our experiments show that this approach outperforms existing solutions in solving text-based games, and it is more sample efficient in terms of the number of interactions with the environment. Moreover, we show that the learned policy can generalize better than existing solutions to unseen games without using any restriction on the action space.

Alexandros Papangelis, Mahdi Namazifar, Chandra Khatri et al.

As the field of Spoken Dialogue Systems and Conversational AI grows, so does the need for tools and environments that abstract away implementation details in order to expedite the development process, lower the barrier of entry to the field, and offer a common test-bed for new ideas. In this paper, we present Plato, a flexible Conversational AI platform written in Python that supports any kind of conversational agent architecture, from standard architectures to architectures with jointly-trained components, single- or multi-party interactions, and offline or online training of any conversational agent component. Plato has been designed to be easy to understand and debug and is agnostic to the underlying learning frameworks that train each component.

Yue Weng, Huaixiu Zheng, Franziska Bell et al.

Smart reply systems have been developed for various messaging platforms. In this paper, we introduce Uber's smart reply system: one-click-chat (OCC), which is a key enhanced feature on top of the Uber in-app chat system. It enables driver-partners to quickly respond to rider messages using smart replies. The smart replies are dynamically selected according to conversation content using machine learning algorithms. Our system consists of two major components: intent detection and reply retrieval, which are very different from standard smart reply systems where the task is to directly predict a reply. It is designed specifically for mobile applications with short and non-canonical messages. Reply retrieval utilizes pairings between intent and reply based on their popularity in chat messages as derived from historical data. For intent detection, a set of embedding and classification techniques are experimented with, and we choose to deploy a solution using unsupervised distributed embedding and nearest-neighbor classifier. It has the advantage of only requiring a small amount of labeled training data, simplicity in developing and deploying to production, and fast inference during serving and hence highly scalable. At the same time, it performs comparably with deep learning architectures such as word-level convolutional neural network. Overall, the system achieves a high accuracy of 76% on intent detection. Currently, the system is deployed in production for English-speaking countries and 71% of in-app communications between riders and driver-partners adopted the smart replies to speedup the communication process.

Alexandros Papangelis, Yi-Chia Wang, Piero Molino et al.

We present the first complete attempt at concurrently training conversational agents that communicate only via self-generated language. Using DSTC2 as seed data, we trained natural language understanding (NLU) and generation (NLG) networks for each agent and let the agents interact online. We model the interaction as a stochastic collaborative game where each agent (player) has a role ("assistant", "tourist", "eater", etc.) and their own objectives, and can only interact via natural language they generate. Each agent, therefore, needs to learn to operate optimally in an environment with multiple sources of uncertainty (its own NLU and NLG, the other agent's NLU, Policy, and NLG). In our evaluation, we show that the stochastic-game agents outperform deep learning based supervised baselines.

Izzeddin Gur, Dilek Hakkani-Tur, Gokhan Tur et al.

We introduce end-to-end neural network based models for simulating users of task-oriented dialogue systems. User simulation in dialogue systems is crucial from two different perspectives: (i) automatic evaluation of different dialogue models, and (ii) training task-oriented dialogue systems. We design a hierarchical sequence-to-sequence model that first encodes the initial user goal and system turns into fixed length representations using Recurrent Neural Networks (RNN). It then encodes the dialogue history using another RNN layer. At each turn, user responses are decoded from the hidden representations of the dialogue level RNN. This hierarchical user simulator (HUS) approach allows the model to capture undiscovered parts of the user goal without the need of an explicit dialogue state tracking. We further develop several variants by utilizing a latent variable model to inject random variations into user responses to promote diversity in simulated user responses and a novel goal regularization mechanism to penalize divergence of user responses from the initial user goal. We evaluate the proposed models on movie ticket booking domain by systematically interacting each user simulator with various dialogue system policies trained with different objectives and users.

Bing Liu, Gokhan Tur, Dilek Hakkani-Tur et al.

In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback on supervised pre-training models. Efficiency of such learning method may suffer from the mismatch of dialogue state distribution between offline training and online interactive learning stages. To address this challenge, we propose a hybrid imitation and reinforcement learning method, with which a dialogue agent can effectively learn from its interaction with users by learning from human teaching and feedback. We design a neural network based task-oriented dialogue agent that can be optimized end-to-end with the proposed learning method. Experimental results show that our end-to-end dialogue agent can learn effectively from the mistake it makes via imitation learning from user teaching. Applying reinforcement learning with user feedback after the imitation learning stage further improves the agent's capability in successfully completing a task.

Bing Liu, Gokhan Tur, Dilek Hakkani-Tur et al.

In this paper, we present a neural network based task-oriented dialogue system that can be optimized end-to-end with deep reinforcement learning (RL). The system is able to track dialogue state, interface with knowledge bases, and incorporate query results into agent's responses to successfully complete task-oriented dialogues. Dialogue policy learning is conducted with a hybrid supervised and deep RL methods. We first train the dialogue agent in a supervised manner by learning directly from task-oriented dialogue corpora, and further optimize it with deep RL during its interaction with users. In the experiments on two different dialogue task domains, our model demonstrates robust performance in tracking dialogue state and producing reasonable system responses. We show that deep RL based optimization leads to significant improvement on task success rate and reduction in dialogue length comparing to supervised training model. We further show benefits of training task-oriented dialogue model end-to-end comparing to component-wise optimization with experiment results on dialogue simulations and human evaluations.

Ankur Bapna, Gokhan Tur, Dilek Hakkani-Tur et al.

State-of-the-art slot filling models for goal-oriented human/machine conversational language understanding systems rely on deep learning methods. While multi-task training of such models alleviates the need for large in-domain annotated datasets, bootstrapping a semantic parsing model for a new domain using only the semantic frame, such as the back-end API or knowledge graph schema, is still one of the holy grail tasks of language understanding for dialogue systems. This paper proposes a deep learning based approach that can utilize only the slot description in context without the need for any labeled or unlabeled in-domain examples, to quickly bootstrap a new domain. The main idea of this paper is to leverage the encoding of the slot names and descriptions within a multi-task deep learned slot filling model, to implicitly align slots across domains. The proposed approach is promising for solving the domain scaling problem and eliminating the need for any manually annotated data or explicit schema alignment. Furthermore, our experiments on multiple domains show that this approach results in significantly better slot-filling performance when compared to using only in-domain data, especially in the low data regime.