Agent-Based Ensemble Reasoning for Repository-Level Issue Resolution

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 EnAgent, the first agent-based ensemble reasoning approach for repository-level issue resolution. EnAgent 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 EnAgent against four state-of-the-art ensemble reasoning techniques. Experimental results demonstrate that EnAgent consistently achieves superior performance, with an average improvement of 10.22% over all baselines in terms of Pass@1. EnAgent has been integrated into Trae Agent, driving it to achieve first place on the SWE-bench Verified leaderboard as of January 2026, with a notable Pass@1 score of 78.80%.