Mudit Verma

Tung Thai, Ming Shen, Mayank Garg et al. · amazon-science

Learning to detect, characterize and accommodate novelties is a challenge that agents operating in open-world domains need to address to be able to guarantee satisfactory task performance. Certain novelties (e.g., changes in environment dynamics) can interfere with the performance or prevent agents from accomplishing task goals altogether. In this paper, we introduce general methods and architectural mechanisms for detecting and characterizing different types of novelties, and for building an appropriate adaptive model to accommodate them utilizing logical representations and reasoning methods. We demonstrate the effectiveness of the proposed methods in evaluations performed by a third party in the adversarial multi-agent board game Monopoly. The results show high novelty detection and accommodation rates across a variety of novelty types, including changes to the rules of the game, as well as changes to the agent's action capabilities.

Utkarsh Soni, Nupur Thakur, Sarath Sreedharan et al.

There is a growing interest in developing automated agents that can work alongside humans. In addition to completing the assigned task, such an agent will undoubtedly be expected to behave in a manner that is preferred by the human. This requires the human to communicate their preferences to the agent. To achieve this, the current approaches either require the users to specify the reward function or the preference is interactively learned from queries that ask the user to compare behavior. The former approach can be challenging if the internal representation used by the agent is inscrutable to the human while the latter is unnecessarily cumbersome for the user if their preference can be specified more easily in symbolic terms. In this work, we propose PRESCA (PREference Specification through Concept Acquisition), a system that allows users to specify their preferences in terms of concepts that they understand. PRESCA maintains a set of such concepts in a shared vocabulary. If the relevant concept is not in the shared vocabulary, then it is learned. To make learning a new concept more feedback efficient, PRESCA leverages causal associations between the target concept and concepts that are already known. In addition, we use a novel data augmentation approach to further reduce required feedback. We evaluate PRESCA by using it on a Minecraft environment and show that it can effectively align the agent with the user's preference.

Mudit Verma, Siddhant Bhambri, Subbarao Kambhampati

Preference Based Reinforcement Learning has shown much promise for utilizing human binary feedback on queried trajectory pairs to recover the underlying reward model of the Human in the Loop (HiL). While works have attempted to better utilize the queries made to the human, in this work we make two observations about the unlabeled trajectories collected by the agent and propose two corresponding loss functions that ensure participation of unlabeled trajectories in the reward learning process, and structure the embedding space of the reward model such that it reflects the structure of state space with respect to action distances. We validate the proposed method on one locomotion domain and one robotic manipulation task and compare with the state-of-the-art baseline PEBBLE. We further present an ablation of the proposed loss components across both the domains and find that not only each of the loss components perform better than the baseline, but the synergic combination of the two has much better reward recovery and human feedback sample efficiency.

Mudit Verma, Ayush Kharkwal, Subbarao Kambhampati

Human-in-the-loop (HiL) reinforcement learning is gaining traction in domains with large action and state spaces, and sparse rewards by allowing the agent to take advice from HiL. Beyond advice accommodation, a sequential decision-making agent must be able to express the extent to which it was able to utilize the human advice. Subsequently, the agent should provide a means for the HiL to inspect parts of advice that it had to reject in favor of the overall environment objective. We introduce the problem of Advice-Conformance Verification which requires reinforcement learning (RL) agents to provide assurances to the human in the loop regarding how much of their advice is being conformed to. We then propose a Tree-based lingua-franca to support this communication, called a Preference Tree. We study two cases of good and bad advice scenarios in MuJoCo's Humanoid environment. Through our experiments, we show that our method can provide an interpretable means of solving the Advice-Conformance Verification problem by conveying whether or not the agent is using the human's advice. Finally, we present a human-user study with 20 participants that validates our method.

Mudit Verma, Subbarao Kambhampati

Preference-based Reinforcement Learning (PbRL) methods utilize binary feedback from the human in the loop (HiL) over queried trajectory pairs to learn a reward model in an attempt to approximate the human's underlying reward function capturing their preferences. In this work, we investigate the issue of a high degree of variability in the initialized reward models which are sensitive to random seeds of the experiment. This further compounds the issue of degenerate reward functions PbRL methods already suffer from. We propose a data-driven reward initialization method that does not add any additional cost to the human in the loop and negligible cost to the PbRL agent and show that doing so ensures that the predicted rewards of the initialized reward model are uniform in the state space and this reduces the variability in the performance of the method across multiple runs and is shown to improve the overall performance compared to other initialization methods.

Mudit Verma, Subbarao Kambhampati

Reinforcement Learning has suffered from poor reward specification, and issues for reward hacking even in simple enough domains. Preference Based Reinforcement Learning attempts to solve the issue by utilizing binary feedbacks on queried trajectory pairs by a human in the loop indicating their preferences about the agent's behavior to learn a reward model. In this work, we present a state augmentation technique that allows the agent's reward model to be robust and follow an invariance consistency that significantly improved performance, i.e. the reward recovery and subsequent return computed using the learned policy over our baseline PEBBLE. We validate our method on three domains, Mountain Car, a locomotion task of Quadruped-Walk, and a robotic manipulation task of Sweep-Into, and find that using the proposed augmentation the agent not only benefits in the overall performance but does so, quite early in the agent's training phase.

Mudit Verma, Katherine Metcalf

Specifying rewards for reinforcement learned (RL) agents is challenging. Preference-based RL (PbRL) mitigates these challenges by inferring a reward from feedback over sets of trajectories. However, the effectiveness of PbRL is limited by the amount of feedback needed to reliably recover the structure of the target reward. We present the PRIor Over Rewards (PRIOR) framework, which incorporates priors about the structure of the reward function and the preference feedback into the reward learning process. Imposing these priors as soft constraints on the reward learning objective reduces the amount of feedback required by half and improves overall reward recovery. Additionally, we demonstrate that using an abstract state space for the computation of the priors further improves the reward learning and the agent's performance.

Mudit Verma, Katherine Metcalf

Preference based Reinforcement Learning (PbRL) removes the need to hand specify a reward function by learning a reward from preference feedback over policy behaviors. Current approaches to PbRL do not address the credit assignment problem inherent in determining which parts of a behavior most contributed to a preference, which result in data intensive approaches and subpar reward functions. We address such limitations by introducing a credit assignment strategy (Hindsight PRIOR) that uses a world model to approximate state importance within a trajectory and then guides rewards to be proportional to state importance through an auxiliary predicted return redistribution objective. Incorporating state importance into reward learning improves the speed of policy learning, overall policy performance, and reward recovery on both locomotion and manipulation tasks. For example, Hindsight PRIOR recovers on average significantly (p<0.05) more reward on MetaWorld (20%) and DMC (15%). The performance gains and our ablations demonstrate the benefits even a simple credit assignment strategy can have on reward learning and that state importance in forward dynamics prediction is a strong proxy for a state's contribution to a preference decision. Code repository can be found at https://github.com/apple/ml-rlhf-hindsight-prior.

Gheorghe Comanici, Eric Bieber, Mike Schaekermann et al. · amazon-science, baidu

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

Subbarao Kambhampati, Karthik Valmeekam, Lin Guan et al.

There is considerable confusion about the role of Large Language Models (LLMs) in planning and reasoning tasks. On one side are over-optimistic claims that LLMs can indeed do these tasks with just the right prompting or self-verification strategies. On the other side are perhaps over-pessimistic claims that all that LLMs are good for in planning/reasoning tasks are as mere translators of the problem specification from one syntactic format to another, and ship the problem off to external symbolic solvers. In this position paper, we take the view that both these extremes are misguided. We argue that auto-regressive LLMs cannot, by themselves, do planning or self-verification (which is after all a form of reasoning), and shed some light on the reasons for misunderstandings in the literature. We will also argue that LLMs should be viewed as universal approximate knowledge sources that have much more meaningful roles to play in planning/reasoning tasks beyond simple front-end/back-end format translators. We present a vision of {\bf LLM-Modulo Frameworks} that combine the strengths of LLMs with external model-based verifiers in a tighter bi-directional interaction regime. We will show how the models driving the external verifiers themselves can be acquired with the help of LLMs. We will also argue that rather than simply pipelining LLMs and symbolic components, this LLM-Modulo Framework provides a better neuro-symbolic approach that offers tighter integration between LLMs and symbolic components, and allows extending the scope of model-based planning/reasoning regimes towards more flexible knowledge, problem and preference specifications.

Divya Pathak, Harshit Kumar, Anuska Roy et al.

Multi-Agentic AI systems, powered by large language models (LLMs), are inherently non-deterministic and prone to silent failures such as drift, cycles, and missing details in outputs, which are difficult to detect. We introduce the task of anomaly detection in agentic trajectories to identify these failures and present a dataset curation pipeline that captures user behavior, agent non-determinism, and LLM variation. Using this pipeline, we curate and label two benchmark datasets comprising \textbf{4,275 and 894} trajectories from Multi-Agentic AI systems. Benchmarking anomaly detection methods on these datasets, we show that supervised (XGBoost) and semi-supervised (SVDD) approaches perform comparably, achieving accuracies up to 98% and 96%, respectively. This work provides the first systematic study of anomaly detection in Multi-Agentic AI systems, offering datasets, benchmarks, and insights to guide future research.

Felix George, Harshit Kumar, Divya Pathak et al.

Agentic applications powered by Large Language Models exhibit non-deterministic behaviors that can form hidden execution cycles, silently consuming resources without triggering explicit errors. Traditional observability platforms fail to detect these costly inefficiencies. We present an unsupervised cycle detection framework that combines structural and semantic analysis. Our approach first applies computationally efficient temporal call stack analysis to identify explicit loops and then leverages semantic similarity analysis to uncover subtle cycles characterized by redundant content generation. Evaluated on 1575 trajectories from a LangGraph-based stock market application, our hybrid approach achieves an F1 score of 0.72 (precision: 0.62, recall: 0.86), significantly outperforming individual structural (F1: 0.08) and semantic methods (F1: 0.28). While these results are encouraging, there remains substantial scope for improvement, and future work is needed to refine the approach and address its current limitations.

Mudit Verma, Siddhant Bhambri, Subbarao Kambhampati

Large Language Models have shown exceptional generative abilities in various natural language and generation tasks. However, possible anthropomorphization and leniency towards failure cases have propelled discussions on emergent abilities of Large Language Models especially on Theory of Mind (ToM) abilities in Large Language Models. While several false-belief tests exists to verify the ability to infer and maintain mental models of another entity, we study a special application of ToM abilities that has higher stakes and possibly irreversible consequences : Human Robot Interaction. In this work, we explore the task of Perceived Behavior Recognition, where a robot employs a Large Language Model (LLM) to assess the robot's generated behavior in a manner similar to human observer. We focus on four behavior types, namely - explicable, legible, predictable, and obfuscatory behavior which have been extensively used to synthesize interpretable robot behaviors. The LLMs goal is, therefore to be a human proxy to the agent, and to answer how a certain agent behavior would be perceived by the human in the loop, for example "Given a robot's behavior X, would the human observer find it explicable?". We conduct a human subject study to verify that the users are able to correctly answer such a question in the curated situations (robot setting and plan) across five domains. A first analysis of the belief test yields extremely positive results inflating ones expectations of LLMs possessing ToM abilities. We then propose and perform a suite of perturbation tests which breaks this illusion, i.e. Inconsistent Belief, Uninformative Context and Conviction Test. We conclude that, the high score of LLMs on vanilla prompts showcases its potential use in HRI settings, however to possess ToM demands invariance to trivial or irrelevant perturbations in the context which LLMs lack.

Mudit Verma, Siddhant Bhambri, Subbarao Kambhampati

The reasoning abilities of Large Language Models (LLMs) remain a topic of debate. Some methods such as ReAct-based prompting, have gained popularity for claiming to enhance sequential decision-making abilities of agentic LLMs. However, it is unclear what is the source of improvement in LLM reasoning with ReAct based prompting. In this paper we examine these claims of ReAct based prompting in improving agentic LLMs for sequential decision-making. By introducing systematic variations to the input prompt we perform a sensitivity analysis along the claims of ReAct and find that the performance is minimally influenced by the "interleaving reasoning trace with action execution" or the content of the generated reasoning traces in ReAct, contrary to original claims and common usage. Instead, the performance of LLMs is driven by the similarity between input example tasks and queries, implicitly forcing the prompt designer to provide instance-specific examples which significantly increases the cognitive burden on the human. Our investigation shows that the perceived reasoning abilities of LLMs stem from the exemplar-query similarity and approximate retrieval rather than any inherent reasoning abilities.

Saurabh Jha, Rohan Arora, Yuji Watanabe et al. · ibm-research

Realizing the vision of using AI agents to automate critical IT tasks depends on the ability to measure and understand effectiveness of proposed solutions. We introduce ITBench, a framework that offers a systematic methodology for benchmarking AI agents to address real-world IT automation tasks. Our initial release targets three key areas: Site Reliability Engineering (SRE), Compliance and Security Operations (CISO), and Financial Operations (FinOps). The design enables AI researchers to understand the challenges and opportunities of AI agents for IT automation with push-button workflows and interpretable metrics. ITBench includes an initial set of 94 real-world scenarios, which can be easily extended by community contributions. Our results show that agents powered by state-of-the-art models resolve only 13.8% of SRE scenarios, 25.2% of CISO scenarios, and 0% of FinOps scenarios. We expect ITBench to be a key enabler of AI-driven IT automation that is correct, safe, and fast.

Atharva Gundawar, Karthik Valmeekam, Mudit Verma et al.

Previous work has attempted to boost Large Language Model (LLM) performance on planning and scheduling tasks through a variety of prompt engineering techniques. While these methods can work within the distributions tested, they are neither robust nor predictable. This limitation can be addressed through compound LLM architectures where LLMs work in conjunction with other components to ensure reliability. In this paper, we present a technical evaluation of a compound LLM architecture--the LLM-Modulo framework. In this framework, an LLM is paired with a complete set of sound verifiers that validate its output, re-prompting it if it fails. This approach ensures that the system can never output any fallacious output, and therefore that every output generated is guaranteed correct--something previous techniques have not been able to claim. Our results, evaluated across four scheduling domains, demonstrate significant performance gains with the LLM-Modulo framework using various models. Additionally, we explore modifications to the base configuration of the framework and assess their impact on overall system performance.

Siddhant Bhambri, Mudit Verma, Upasana Biswas et al.

Preference-based Reinforcement Learning (PbRL) has made significant strides in single-agent settings, but has not been studied for multi-agent frameworks. On the other hand, modeling cooperation between multiple agents, specifically, Human-AI Teaming settings while ensuring successful task completion is a challenging problem. To this end, we perform the first investigation of multi-agent PbRL by extending single-agent PbRL to the two-agent teaming settings and formulate it as a Human-AI PbRL Cooperation Game, where the RL agent queries the human-in-the-loop to elicit task objective and human's preferences on the joint team behavior. Under this game formulation, we first introduce the notion of Human Flexibility to evaluate team performance based on if humans prefer to follow a fixed policy or adapt to the RL agent on the fly. Secondly, we study the RL agent's varying access to the human policy. We highlight a special case along these two dimensions, which we call Specified Orchestration, where the human is least flexible and agent has complete access to human policy. We motivate the need for taking Human Flexibility into account and the usefulness of Specified Orchestration through a gamified user study. We evaluate state-of-the-art PbRL algorithms for Human-AI cooperative setups through robot locomotion based domains that explicitly require forced cooperation. Our findings highlight the challenges associated with PbRL by varying Human Flexibility and agent's access to the human policy. Finally, we draw insights from our user study and empirical results, and conclude that Specified Orchestration can be seen as an upper bound PbRL performance for future research in Human-AI teaming scenarios.

Subbarao Kambhampati, Sarath Sreedharan, Mudit Verma et al.

Despite the surprising power of many modern AI systems that often learn their own representations, there is significant discontent about their inscrutability and the attendant problems in their ability to interact with humans. While alternatives such as neuro-symbolic approaches have been proposed, there is a lack of consensus on what they are about. There are often two independent motivations (i) symbols as a lingua franca for human-AI interaction and (ii) symbols as system-produced abstractions used by the AI system in its internal reasoning. The jury is still out on whether AI systems will need to use symbols in their internal reasoning to achieve general intelligence capabilities. Whatever the answer there is, the need for (human-understandable) symbols in human-AI interaction seems quite compelling. Symbols, like emotions, may well not be sine qua non for intelligence per se, but they will be crucial for AI systems to interact with us humans -- as we can neither turn off our emotions nor get by without our symbols. In particular, in many human-designed domains, humans would be interested in providing explicit (symbolic) knowledge and advice -- and expect machine explanations in kind. This alone requires AI systems to to maintain a symbolic interface for interaction with humans. In this blue sky paper, we argue this point of view, and discuss research directions that need to be pursued to allow for this type of human-AI interaction.

Sriram Gopalakrishnan, Mudit Verma, Subbarao Kambhampati

When humans are given a policy to execute, there can be policy execution errors and deviations in policy if there is uncertainty in identifying a state. This can happen due to the human agent's cognitive limitations and/or perceptual errors. So an algorithm that computes a policy for a human to execute ought to consider these effects in its computations. An optimal Markov Decision Process (MDP) policy that is poorly executed (because of a human agent) maybe much worse than another policy that is suboptimal in the MDP, but considers the human-agent's execution behavior. In this paper we consider two problems that arise from state uncertainty; these are erroneous state-inference, and extra-sensing actions that a person might take as a result of their uncertainty. We present a framework to model the human agent's behavior with respect to state uncertainty, and can be used to compute MDP policies that accounts for these problems. This is followed by a hill climbing algorithm to search for good policies given our model of the human agent. We also present a branch and bound algorithm which can find the optimal policy for such problems. We show experimental results in a Gridworld domain, and warehouse-worker domain. Finally, we present human-subject studies that support our human model assumptions.

Zahra Zahedi, Mudit Verma, Sarath Sreedharan et al.

Trust between team members is an essential requirement for any successful cooperation. Thus, engendering and maintaining the fellow team members' trust becomes a central responsibility for any member trying to not only successfully participate in the task but to ensure the team achieves its goals. The problem of trust management is particularly challenging in mixed human-robot teams where the human and the robot may have different models about the task at hand and thus may have different expectations regarding the current course of action and forcing the robot to focus on the costly explicable behavior. We propose a computational model for capturing and modulating trust in such longitudinal human-robot interaction, where the human adopts a supervisory role. In our model, the robot integrates human's trust and their expectations from the robot into its planning process to build and maintain trust over the interaction horizon. By establishing the required level of trust, the robot can focus on maximizing the team goal by eschewing explicit explanatory or explicable behavior without worrying about the human supervisor monitoring and intervening to stop behaviors they may not necessarily understand. We model this reasoning about trust levels as a meta reasoning process over individual planning tasks. We additionally validate our model through a human subject experiment.

Mudit Verma, Pradyumna Sinha, Karan Goyal et al.

Neural networks have now long been used for solving complex problems of image domain, yet designing the same needs manual expertise. Furthermore, techniques for automatically generating a suitable deep learning architecture for a given dataset have frequently made use of reinforcement learning and evolutionary methods which take extensive computational resources and time. We propose a new framework for neural architecture search based on a hill-climbing procedure using morphism operators that makes use of a novel gradient update scheme. The update is based on the aging of neural network layers and results in the reduction in the overall training time. This technique can search in a broader search space which subsequently yields competitive results. We achieve a 4.96% error rate on the CIFAR-10 dataset in 19.4 hours of a single GPU training.

Mudit Verma, Arun Balaji Buduru

Due to a drastic improvement in the quality of internet services worldwide, there is an explosion of multilingual content generation and consumption. This is especially prevalent in countries with large multilingual audience, who are increasingly consuming media outside their linguistic familiarity/preference. Hence, there is an increasing need for real-time and fine-grained content analysis services, including language identification, content transcription, and analysis. Accurate and fine-grained spoken language detection is an essential first step for all the subsequent content analysis algorithms. Current techniques in spoken language detection may lack on one of these fronts: accuracy, fine-grained detection, data requirements, manual effort in data collection \& pre-processing. Hence in this work, a real-time language detection approach to detect spoken language from 5 seconds' audio clips with an accuracy of 91.8\% is presented with exiguous data requirements and minimal pre-processing. Novel architectures for Capsule Networks is proposed which operates on spectrogram images of the provided audio snippets. We use previous approaches based on Recurrent Neural Networks and iVectors to present the results. Finally we show a ``Non-Class'' analysis to further stress on why CapsNet architecture works for LID task.

Lin Guan, Mudit Verma, Sihang Guo et al.

Human explanation (e.g., in terms of feature importance) has been recently used to extend the communication channel between human and agent in interactive machine learning. Under this setting, human trainers provide not only the ground truth but also some form of explanation. However, this kind of human guidance was only investigated in supervised learning tasks, and it remains unclear how to best incorporate this type of human knowledge into deep reinforcement learning. In this paper, we present the first study of using human visual explanations in human-in-the-loop reinforcement learning (HRL). We focus on the task of learning from feedback, in which the human trainer not only gives binary evaluative "good" or "bad" feedback for queried state-action pairs, but also provides a visual explanation by annotating relevant features in images. We propose EXPAND (EXPlanation AugmeNted feeDback) to encourage the model to encode task-relevant features through a context-aware data augmentation that only perturbs irrelevant features in human salient information. We choose five tasks, namely Pixel-Taxi and four Atari games, to evaluate the performance and sample efficiency of this approach. We show that our method significantly outperforms methods leveraging human explanation that are adapted from supervised learning, and Human-in-the-loop RL baselines that only utilize evaluative feedback.

Sarath Sreedharan, Utkarsh Soni, Mudit Verma et al.

As increasingly complex AI systems are introduced into our daily lives, it becomes important for such systems to be capable of explaining the rationale for their decisions and allowing users to contest these decisions. A significant hurdle to allowing for such explanatory dialogue could be the vocabulary mismatch between the user and the AI system. This paper introduces methods for providing contrastive explanations in terms of user-specified concepts for sequential decision-making settings where the system's model of the task may be best represented as an inscrutable model. We do this by building partial symbolic models of a local approximation of the task that can be leveraged to answer the user queries. We test these methods on a popular Atari game (Montezuma's Revenge) and variants of Sokoban (a well-known planning benchmark) and report the results of user studies to evaluate whether people find explanations generated in this form useful.

Mudit Verma, Siddhant Bhambri, Saurabh Gupta et al.

Rapid advancements in the Internet of Things (IoT) have facilitated more efficient deployment of smart environment solutions for specific user requirement. With the increase in the number of IoT devices, it has become difficult for the user to control or operate every individual smart device into achieving some desired goal like optimized power consumption, scheduled appliance running time, etc. Furthermore, existing solutions to automatically adapt the IoT devices are not capable enough to incorporate the user behavior. This paper presents a novel approach to accurately configure IoT devices while achieving the twin objectives of energy optimization along with conforming to user preferences. Our work comprises of unsupervised clustering of devices' data to find the states of operation for each device, followed by probabilistically analyzing user behavior to determine their preferred states. Eventually, we deploy an online reinforcement learning (RL) agent to find the best device settings automatically. Results for three different smart homes' data-sets show the effectiveness of our methodology. To the best of our knowledge, this is the first time that a practical approach has been adopted to achieve the above mentioned objectives without any human interaction within the system.