{"ID":2888289,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.23370","arxiv_id":"2507.23370","title":"Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling","abstract":"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 project to support the research community, with all resources available at https://github.com/bytedance/trae-agent.","short_abstract":"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 rea...","url_abs":"https://arxiv.org/abs/2507.23370","url_pdf":"https://arxiv.org/pdf/2507.23370v1","authors":"[\"Trae Research Team\",\"Pengfei Gao\",\"Zhao Tian\",\"Xiangxin Meng\",\"Xinchen Wang\",\"Ruida Hu\",\"Yuanan Xiao\",\"Yizhou Liu\",\"Zhao Zhang\",\"Junjie Chen\",\"Cuiyun Gao\",\"Yun Lin\",\"Yingfei Xiong\",\"Chao Peng\",\"Xia Liu\"]","published":"2025-07-31T09:37:22Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":611526,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2888289,"paper_url":"https://arxiv.org/abs/2507.23370","paper_title":"Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling","repo_url":"https://github.com/bytedance/trae-agent","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}