13 citations · 20 across the 23 of their papers we have counts for
23 papers
Turning Interaction History into Execution State: A Runtime Layer for Long-Horizon Coding Agents
Zehao Wang, Yisen Xu, Chenglin Li +5
Long-horizon coding agents accumulate hundreds of actions and observations in their trajectories, yet nothing in this record indicates which observations still describe the reposit…
Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance
Chao Peng, Zhiheng Lyu, Peijie Dong +2
Long-horizon benchmarks often show that agents fail more as tasks become longer. This observation is useful for deployment, but it does not by itself explain why failure occurs. Mo…
How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study
Yunbo Lyu, David Williams, Jieke Shi +5
The rise of Software Engineering (SE) agents, i.e., LLM-based agents that can understand large codebases and carry out engineering tasks with limited human intervention, has been m…
SetupX: Can LLM Agents Learn from Past Failures in Functionality-Correct Code Repository Setup?
Zihang Zhou, Ziqian Ren, Yukai Wu +7
Functionality-correct repository setup aims to configure execution environments (e.g., dependencies, build scripts) to successfully execute a repository's documented features. It p…
Yunjue Agent Tech Report: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks
Haotian Li, Shijun Yang, Weizhen Qi +5
Conventional agent systems often struggle in open-ended environments where task distributions continuously drift and external supervision is scarce. Their reliance on static toolse…
Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
Zhi Chen, Zhensu Sun, Yuling Shi +4
Large Language Model (LLM) code agents increasingly resolve repository-level issues by iteratively editing code, invoking tools, and validating candidate patches. In these workflow…
AdaGReS:Adaptive Greedy Context Selection via Redundancy-Aware Scoring for Token-Budgeted RAG
Chao Peng, Bin Wang, Zhilei Long +1
Retrieval-augmented generation (RAG) is highly sensitive to the quality of selected context, yet standard top-k retrieval often returns redundant or near-duplicate chunks that wast…
GraphLocator: Graph-guided Causal Reasoning for Issue Localization
Wei Liu, Chao Peng, Pengfei Gao +4
The issue localization task aims to identify the locations in a software repository that requires modification given a natural language issue description. This task is fundamental…
More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents
Pengfei Gao, Chao Peng
LLM-powered coding agents, which operate in iterative loops (turns) to solve software engineering tasks, are becoming increasingly powerful. However, their practical deployment is…
Scalable Supervision for Software Agents via Patch Reasoning
Junjielong Xu, Boyin Tan, Xiaoyuan Liu +3
While language model agents have advanced software engineering, existing test-based supervision is limiting its scalability on real-world issues. The reason is twofold: (1) high-co…
Extending Fill-In-the-Middle with Instructions for Steerable Code Completion
Zhensu Sun, Chengran Yang, Chao Peng +4
Code completion models often fail when the developer's intent is under-specified in the code context. To mitigate this, developers frequently use natural language comments to clari…
Reducing Cost of LLM Agents with Trajectory Reduction
Yuan-An Xiao, Pengfei Gao, Chao Peng +1
Multi-turn agent systems based on Large Language Models (LLMs) have become increasingly popular for software engineering tasks. While LLM agents demonstrate promising effectiveness…
Tool-integrated Reinforcement Learning for Repo Deep Search
Zexiong Ma, Chao Peng, Qunhong Zeng +3
Issue localization, the process of identifying code locations that need modification to resolve software issues, is a critical yet challenging task in software development. The sem…
Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling
Trae Research Team, Pengfei Gao, Zhao Tian +12
Software issue resolution is a critical challenge in software engineering and has garnered increasing attention in recent years. With the rapid advancement of large language models…
SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code
Xinghang Li, Jingzhe Ding, Chao Peng +4
The code generation capabilities of large language models(LLMs) have emerged as a critical dimension in evaluating their overall performance. However, prior research has largely ov…
CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation
Xinchen Wang, Pengfei Gao, Chao Peng +2
Large language models (LLMs) have demonstrated strong capabilities in code generation, underscoring the critical need for rigorous and comprehensive evaluation. Existing evaluation…
SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning
Zexiong Ma, Chao Peng, Pengfei Gao +3
Mainstream issue-resolving frameworks predominantly rely on commercial models, leading to high costs and privacy concerns. Existing training approaches for issue resolving struggle…
Repo2Run: Automated Building Executable Environment for Code Repository at Scale
Ruida Hu, Chao Peng, Xinchen Wang +2
Scaling up executable code data is significant for improving language models' software engineering capability. The intricate nature of the process makes it labor-intensive, time-co…
A Real-World Benchmark for Evaluating Fine-Grained Issue Solving Capabilities of Large Language Models
Ruida Hu, Chao Peng, Jingyi Ren +6
Automatically resolving software issues is crucial for software development in practice, impacting the software quality and user experience. The process of resolving real-world iss…
AEGIS: An Agent-based Framework for General Bug Reproduction from Issue Descriptions
Xinchen Wang, Pengfei Gao, Xiangxin Meng +4
In software maintenance, bug reproduction is essential for effective fault localization and repair. Manually writing reproduction scripts is a time-consuming task with high require…
An Empirical Study on LLM-based Agents for Automated Bug Fixing
Xiangxin Meng, Zexiong Ma, Pengfei Gao +1
Large language models (LLMs) and LLM-based Agents have been applied to fix bugs automatically, demonstrating the capability in addressing software defects by engaging in developmen…
MarsCode Agent: AI-native Automated Bug Fixing
Yizhou Liu, Pengfei Gao, Xinchen Wang +4
Recent advances in large language models (LLMs) have shown significant potential to automate various software development tasks, including code completion, test generation, and bug…
CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility
Guohai Xu, Jiayi Liu, Ming Yan +11
With the rapid evolution of large language models (LLMs), there is a growing concern that they may pose risks or have negative social impacts. Therefore, evaluation of human values…