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.

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.

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.

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.