Jiri Gesi

Jiri Gesi, Siqi Liu, Jiawei Li et al.

As Deep learning (DL) systems continuously evolve and grow, assuring their quality becomes an important yet challenging task. Compared to non-DL systems, DL systems have more complex team compositions and heavier data dependency. These inherent characteristics would potentially cause DL systems to be more vulnerable to bugs and, in the long run, to maintenance issues. Code smells are empirically tested as efficient indicators of non-DL systems. Therefore, we took a step forward into identifying code smells, and understanding their impact on maintenance in this comprehensive study. This is the first study on investigating code smells in the context of DL software systems, which helps researchers and practitioners to get a first look at what kind of maintenance modification made and what code smells developers have been dealing with. Our paper has three major contributions. First, we comprehensively investigated the maintenance modifications that have been made by DL developers via studying the evolution of DL systems, and we identified nine frequently occurred maintenance-related modification categories in DL systems. Second, we summarized five code smells in DL systems. Third, we validated the prevalence, and the impact of our newly identified code smells through a mixture of qualitative and quantitative analysis. We found that our newly identified code smells are prevalent and impactful on the maintenance of DL systems from the developer's perspective.

Yuxuan Lu, Jing Huang, Yan Han et al.

Recent research shows that LLM Agents can generate ``believable'' human behaviors via prompt-only methods, and such agents have been increasingly adopted in downstream applications. However, existing evaluation of these agents only focuses on qualitative believability (whether human raters think they are accurate), leaving open questions of whether LLM agents can accurately generate step-by-step actions mimicking a particular human's behavior in a multi-turn interaction task. In this work, we take shopping as a case study and present the first large-scale quantitative evaluation of state-of-the-art LLMs' ability to accurately simulate human behavior. Using real-world data from 31,865 online shopping sessions containing 230,965 user actions, our evaluation reveals that prompt-based LLMs (DeepSeek-R1, Llama, Claude) achieve only 11.86% accuracy in generating human actions, highlighting a substantial gap in actual behavioral accuracy. Through experiments, we also showcase that strategies as simple as fine-tuning LLMs on real human click-through data augmented with synthesized reasoning traces can greatly enhance models' performance. The fine-tuned Qwen2.5-7B achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing substantial improvements of 5.4% and 13.85% over prompt-only baselines. This work establishes the first rigorous benchmark for human behavior simulation and provides actionable insights for developing more accurate LLM agents for future downstream applications.

Yong Lin, Shange Tang, Bohan Lyu et al. · uw

We introduce Goedel-Prover-V2, a series of open-source language models that set a new state-of-the-art in automated theorem proving. Built on the standard expert iteration and reinforcement learning pipeline, our approach incorporates three key innovations: (1) Scaffolded data synthesis: We generate synthetic tasks of increasing difficulty to train the model to master increasingly complex theorems; (2) Verifier-guided self-correction: We enable the model to iteratively revise its proofs by leveraging feedback from the Lean compiler; (3) Model averaging: We merge model checkpoints to mitigate the decrease in model output diversity in later stages of training. Our small model, Goedel-Prover-V2-8B, reaches 84.6% pass@32 on MiniF2F and outperforms DeepSeek-Prover-V2-671B under the same metric, despite being 80X smaller. Our flagship model, Goedel-Prover-V2-32B, achieves 88.1% on MiniF2F at pass@32 in standard mode and 90.4% in self-correction mode, outperforming prior SOTA by a large margin. Additionally, our flagship model solves 86 problems on PutnamBench at pass@184, securing the first place among open-source models on the leaderboard, surpassing DeepSeek-Prover-V2-671B's record of solving 47 problems by pass@1024 with a significantly smaller model size and compute budget. At the time of its release (July-August 2025), Goedel-Prover-V2 achieves the strongest overall performance among all open-source theorem provers. It also ranks among the top-performing models--including closed-source systems with publicly reported performance--under a constrained test-time compute budget. Our models, code, and data are released at https://github.com/Goedel-LM/Goedel-Prover-V2.

Wenhao Huang, Qingwen Zeng, Qiyue Chen et al.

Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inference cost. While prior work has focused on improving inference efficiency through system-level optimizations or prompt engineering, we argue that a key bottleneck lies in the representation of the action space itself. We propose Latent Action Reparameterization (LAR), a framework that learns a compact latent action space in which each latent action corresponds to a multi-step semantic behavior. By reparameterizing agent actions into latent units, LAR enables decision making over a shorter effective horizon while preserving the expressiveness of the original action space. Unlike hand-crafted macros or hierarchical controllers, latent actions are learned from agent trajectories and integrated directly into the model, allowing both planning and execution to operate over abstract action representations. Across a range of LLM-based agent benchmarks, LAR significantly reduces the effective action horizon and improves inference efficiency under fixed compute budgets. As a consequence, our approach achieves substantial reductions in action tokens and corresponding wall-clock inference time, while maintaining or improving task success rates. These results suggest that action representation learning is a critical and underexplored factor in scaling efficient LLM agent inference, complementary to advances in model architecture and hardware.

Yuxuan Lu, Ziyi Wang, Yingzhou Lu et al.

Training tool-calling agents requires large-scale trajectory data with verifiable labels, yet existing approaches either synthesize environments that diverge from real API behavior or generate tasks without ground-truth outcomes for verification. We present FireFly, a pipeline for generating verified tool-call data from real-world MCP servers. Our key insight is to invert the standard synthesis pipeline: rather than generating tasks and hoping they are solvable, we first let a strong LLM explore real APIs along graph-guided DAG structures, then synthesize tasks backward from observed outcomes, guaranteeing label correctness by construction. To handle the scale of real-world tool spaces (${\sim}$1,000 tools), we build a pairwise tool graph and sample sub-DAGs to focus exploration on semantically coherent workflows. To address environment drift in live APIs, we construct a retrieval-augmented simulator that caches all exploration results and replays them during training and evaluation, enabling fully offline and reproducible RL. Applying this pipeline yields 5,144 verified tasks spanning 240 servers and 993 tools. A 4B-parameter model trained with GRPO on FireFly matches Claude Sonnet 4.6 on our held-out test set and shows improvements on multiple tool-calling benchmarks including Tau2-Bench, MCPMark, and MCP-Atlas.

Ziyi Wang, Yuxuan Lu, Yimeng Zhang et al.

Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized settings with general, fixed, and well-specified tasks. In real-world applications, user requests are often (1) ambiguous, (2) changing over time, or (3) infeasible due to policy constraints, and training and evaluation data that cover these diverse, complex interaction patterns remain under-represented. To bridge the gap, we present Trajectory2Task, a verifiable data generation pipeline for studying tool use at scale under three realistic user scenarios: ambiguous intent, changing intent, and infeasible intents. The pipeline first conducts multi-turn exploration to produce valid tool-call trajectories. It then converts these trajectories into user-facing tasks with controlled intent adaptations. This process yields verifiable task that support closed-loop evaluation and training. We benchmark seven state-of-the-art LLMs on the generated complex user scenario tasks and observe frequent failures. Finally, using successful trajectories obtained from task rollouts, we fine-tune lightweight LLMs and find consistent improvements across all three conditions, along with better generalization to unseen tool-use domains, indicating stronger general tool-calling ability.

Yuxuan Lu, Bingsheng Yao, Hansu Gu et al.

Usability testing is a fundamental yet challenging (e.g., inflexible to iterate the study design flaws and hard to recruit study participants) research method for user experience (UX) researchers to evaluate a web design. Recent advances in Large Language Model-simulated Agent (LLM-Agent) research inspired us to design UXAgent to support UX researchers in evaluating and reiterating their usability testing study design before they conduct the real human subject study. Our system features an LLM-Agent module and a universal browser connector module so that UX researchers can automatically generate thousands of simulated users to test the target website. The results are shown in qualitative (e.g., interviewing how an agent thinks ), quantitative (e.g., # of actions), and video recording formats for UX researchers to analyze. Through a heuristic user evaluation with five UX researchers, participants praised the innovation of our system but also expressed concerns about the future of LLM Agent-assisted UX study.

Jiaju Chen, Yuxuan Lu, Xiaojie Wang et al.

Nearly all human work is collaborative; thus, the evaluation of real-world NLP applications often requires multiple dimensions that align with diverse human perspectives. As real human evaluator resources are often scarce and costly, the emerging "LLM-as-a-judge" paradigm sheds light on a promising approach to leverage LLM agents to believably simulate human evaluators. Yet, to date, existing LLM-as-a-judge approaches face two limitations: persona descriptions of agents are often arbitrarily designed, and the frameworks are not generalizable to other tasks. To address these challenges, we propose MAJ-EVAL, a Multi-Agent-as-Judge evaluation framework that can automatically construct multiple evaluator personas with distinct dimensions from relevant text documents (e.g., research papers), instantiate LLM agents with the personas, and engage in-group debates with multi-agents to Generate multi-dimensional feedback. Our evaluation experiments in both the educational and medical domains demonstrate that MAJ-EVAL can generate evaluation results that better align with human experts' ratings compared with conventional automated evaluation metrics and existing LLM-as-a-judge methods.

Ziyi Wang, Yuxuan Lu, Wenbo Li et al. · gatech, microsoft-research

Can large language models (LLMs) accurately simulate the next web action of a specific user? While LLMs have shown promising capabilities in generating ``believable'' human behaviors, evaluating their ability to mimic real user behaviors remains an open challenge, largely due to the lack of high-quality, publicly available datasets that capture both the observable actions and the internal reasoning of an actual human user. To address this gap, we introduce OPERA, a novel dataset of Observation, Persona, Rationale, and Action collected from real human participants during online shopping sessions. OPERA is the first public dataset that comprehensively captures: user personas, browser observations, fine-grained web actions, and self-reported just-in-time rationales. We developed both an online questionnaire and a custom browser plugin to gather this dataset with high fidelity. Using OPERA, we establish the first benchmark to evaluate how well current LLMs can predict a specific user's next action and rationale with a given persona and <observation, action, rationale> history. This dataset lays the groundwork for future research into LLM agents that aim to act as personalized digital twins for human.

Yuxuan Lu, Bingsheng Yao, Hansu Gu et al.

Usability testing is a fundamental research method that user experience (UX) researchers use to evaluate and iterate their new designs. But what about evaluating and iterating the usability testing study design itself? Recent advances in Large Language Model-simulated Agent (LLM Agent) research inspired us to design UXAgent to support UX researchers in evaluating and iterating their study design before they conduct the real human-subject study. Our system features a Persona Generator module, an LLM Agent module, and a Universal Browser Connector module to automatically generate thousands of simulated users and to interactively test the target website. The system also provides a Result Viewer Interface so that the UX researchers can easily review and analyze the generated qualitative (e.g., agents' post-study surveys) and quantitative data (e.g., agents' interaction logs), or even interview agents directly. Through a heuristic evaluation with 16 UX researchers, participants praised the innovation of our system but also expressed concerns about the future of LLM Agent usage in UX studies.

Yuxuan Lu, Jing Huang, Yan Han et al.

Recent research shows that LLM Agents can generate ``believable'' human behaviors via prompt-only methods, and such agents have been increasingly adopted in downstream applications. However, existing evaluation of these agents only focuses on qualitative believability (whether human raters think they are accurate), leaving open questions of whether LLM agents can accurately generate step-by-step actions mimicking a particular human's behavior in a multi-turn interaction task. In this work, we take shopping as a case study and present the first large-scale quantitative evaluation of state-of-the-art LLMs' ability to accurately simulate human behavior. Using real-world data from 31,865 online shopping sessions containing 230,965 user actions, our evaluation reveals that prompt-based LLMs (DeepSeek-R1, Llama, Claude) achieve only 11.86% accuracy in generating human actions, highlighting a substantial gap in actual behavioral accuracy. Through experiments, we also showcase that strategies as simple as fine-tuning LLMs on real human click-through data augmented with synthesized reasoning traces can greatly enhance models' performance. The fine-tuned Qwen2.5-7B achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing substantial improvements of 5.4% and 13.85% over prompt-only baselines. This work establishes the first rigorous benchmark for human behavior simulation and provides actionable insights for developing more accurate LLM agents for future downstream applications.

Yimeng Zhang, Tian Wang, Jiri Gesi et al.

Large Language Models (LLMs) have recently demonstrated strong potential in generating 'believable human-like' behavior in web environments. Prior work has explored augmenting training data with LLM-synthesized rationales and applying supervised fine-tuning (SFT) to enhance reasoning ability, which in turn can improve downstream action prediction. However, the performance of such approaches remains inherently bounded by the reasoning capabilities of the model used to generate the rationales. In this paper, we introduce Shop-R1, a novel reinforcement learning (RL) framework aimed at enhancing the reasoning ability of LLMs for simulation of real human behavior in online shopping environments Specifically, Shop-R1 decomposes the human behavior simulation task into two stages: rationale generation and action prediction, each guided by distinct reward signals. For rationale generation, we leverage internal model signals (e.g., logit distributions) to guide the reasoning process in a self-supervised manner. For action prediction, we propose a hierarchical reward structure with difficulty-aware scaling to prevent reward hacking and enable fine-grained reward assignment. This design evaluates both high-level action types and the correctness of fine-grained sub-action details (attributes and values), rewarding outputs proportionally to their difficulty. Experimental results show that our method achieves a relative improvement of over 65% compared to the baseline.

Lu Sun, Shihan Fu, Bingsheng Yao et al.

Agentic AI is emerging, capable of executing tasks through natural language, such as Copilot for coding or Amazon Rufus for shopping. Evaluating these systems is challenging, as their rapid evolution outpaces traditional human evaluation. Researchers have proposed LLM Agents to simulate participants as digital twins, but it remains unclear to what extent a digital twin can represent a specific customer in multi-turn interaction with an agentic AI system. In this paper, we recruited 40 human participants to shop with Amazon Rufus, collected their personas, interaction traces, and UX feedback, and then created digital twins to repeat the task. Pairwise comparison of human and digital-twin traces shows that while agents often explored more diverse choices, their action patterns aligned with humans and yielded similar design feedback. This study is the first to quantify how closely LLM agents can mirror human multi-turn interaction with an agentic AI system, highlighting their potential for scalable evaluation.

Jiacheng Lin, Zhongruo Wang, Kun Qian et al.

Supervised Fine-Tuning (SFT) on domain-specific datasets is a common approach to adapt Large Language Models (LLMs) to specialized tasks but is often believed to degrade their general capabilities. In this work, we revisit this trade-off and present both empirical and theoretical insights. First, we show that SFT does not always hurt: using a smaller learning rate can substantially mitigate general performance degradation while preserving comparable target-domain performance. We then provide a theoretical analysis that explains these phenomena and further motivates a new method, Token-Adaptive Loss Reweighting (TALR). Building on this, and recognizing that smaller learning rates alone do not fully eliminate general-performance degradation in all cases, we evaluate a range of strategies for reducing general capability loss, including L2 regularization, LoRA, model averaging, FLOW, and our proposed TALR. Experimental results demonstrate that while no method completely eliminates the trade-off, TALR consistently outperforms these baselines in balancing domain-specific gains and general capabilities. Finally, we distill our findings into practical guidelines for adapting LLMs to new domains: (i) using a small learning rate to achieve a favorable trade-off, and (ii) when a stronger balance is further desired, adopt TALR as an effective strategy.

Yimeng Zhang, Jiri Gesi, Ran Xue et al.

LLMs have recently demonstrated strong potential in simulating online shopper behavior. Prior work has improved action prediction by applying SFT on action traces with LLM-generated rationales, and by leveraging RL to further enhance reasoning capabilities. Despite these advances, current approaches rely on text-based inputs and overlook the essential role of visual perception in shaping human decision-making during web GUI interactions. In this paper, we investigate the integration of visual information, specifically webpage screenshots, into behavior simulation via VLMs, leveraging OPeRA dataset. By grounding agent decision-making in both textual and visual modalities, we aim to narrow the gap between synthetic agents and real-world users, thereby enabling more cognitively aligned simulations of online shopping behavior. Specifically, we employ SFT for joint action prediction and rationale generation, conditioning on the full interaction context, which comprises action history, past HTML observations, and the current webpage screenshot. To further enhance reasoning capabilities, we integrate RL with a hierarchical reward structure, scaled by a difficulty-aware factor that prioritizes challenging decision points. Empirically, our studies show that incorporating visual grounding yields substantial gains: the combination of text and image inputs improves exact match accuracy by more than 6% over text-only inputs. These results indicate that multi-modal grounding not only boosts predictive accuracy but also enhances simulation fidelity in visually complex environments, which captures nuances of human attention and decision-making that text-only agents often miss. Finally, we revisit the design space of behavior simulation frameworks, identify key methodological limitations, and propose future research directions toward building efficient and effective human behavior simulators.

Yuxuan Lu, Jing Huang, Hui Liu et al.

Training and evaluation of Reinforcement Learning (RL) web agents have gained increasing attention, yet a scalable and efficient environment that couples realistic and robust browser-side interaction with controllable server-side state at scale is still missing. Existing environments tend to have one or more of the following issues: they overwhelm policy models with excessive and noisy context; they perform actions non-deterministically without waiting for the UI or network to stabilize; or they cannot scale isolated client-server containers effectively for parallel RL rollouts. We propose WEBSERV, an environment that includes 1) a compact, site-agnostic browser environment that balances context and action complexity, and 2) a scalable RL environment via efficient launching and resetting web-servers to enable scalable RL training and evaluation. We evaluate WEBSERV on the shopping CMS and Gitlab tasks in WebArena, achieving state-of-the-art single-prompt success rates while cutting launch latency by ~5x and storage need by ~240x, with a comparable memory footprint, enabling 200+ concurrent containers on a single host.

Jiri Gesi, Iftekhar Ahmed

Transformer-based models have demonstrated considerable potential for source code modeling tasks in software engineering. However, they are limited by their dependence solely on automatic self-attention weight learning mechanisms. Previous studies have shown that these models overemphasize delimiters added by tokenizers (e.g., [CLS], [SEP]), which may lead to overlooking essential information in the original input source code. To address this challenge, we introduce SyntaGuid, a novel approach that utilizes the observation that attention weights tend to be biased towards specific source code syntax tokens and abstract syntax tree (AST) elements in fine-tuned language models when they make correct predictions. SyntaGuid facilitates the guidance of attention-weight learning, leading to improved model performance on various software engineering tasks. We evaluate the effectiveness of SyntaGuid on multiple tasks and demonstrate that it outperforms existing state-of-the-art models in overall performance without requiring additional data. Experimental result shows that SyntaGuid can improve overall performance up to 3.25% and fix up to 28.3% wrong predictions. Our work represents the first attempt to guide the attention of Transformer-based models towards critical source code tokens during fine-tuning, highlighting the potential for enhancing Transformer-based models in software engineering.