Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling

作者：T- Team, Pengfei Gao, Zhao Tian, Xiangxin Meng, Xinchen Wang, Ruida Hu, Xiao, Yuanan, Yizhou Liu, Zhao Zhang, Junjie Chen, Cuiyun Gao, Yunfeng Lin, Yingfei Xiong, Chao Peng, Xia Liu · 发表于：arXiv (Cornell University) · 年份：2025 · DOI：10.48550/arxiv.2507.23370 · 被引用次数：2 · 研究领域：Software System Performance and Reliability、Software Testing and Debugging Techniques、Service-Oriented Architecture and Web Services

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 (LLMs), substantial progress has been made in addressing real-world software engineering tasks. Recent studies have introduced ensemble reasoning techniques to enhance the performance of LLM-based issue resolution. However, existing prompting-based methods still face limitations in effectively exploring large ensemble spaces and lack the capacity for repository-level understanding, both of which constrain their overall effectiveness. In this paper, we propose Trae Agent, the first agent-based ensemble reasoning approach for repository-level issue resolution. Trae Agent formulates our goal as an optimal solution search problem and addresses two key challenges, i.e., large ensemble spaces and repository-level understanding, through modular agents for generation, pruning, and selection. We conduct extensive experiments using three leading LLMs on the widely-adopted SWE-bench benchmark, comparing Trae Agent against four state-of-the-art ensemble reasoning techniques. Experimental results demonstrate that Trae Agent consistently achieves superior performance, with an average improvement of 10.22% over all baselines in terms of Pass@1. Trae Agent has achieved first place on the SWE-bench Verified leaderboard, with a notable Pass@1 score of 75.20%. We are pleased to release Trae Agent as an open-source pr...