Software engineers resolving repository-level issues do not treat existing tests as immutable correctness oracles. Instead, they iteratively refine both code and the tests used to characterize intended behavior, as new modifications expose missing assumptions or misinterpreted failure conditions. In contrast, most existing large language model (LLM)-based repair systems adopt a linear pipeline in which tests or other validation signals act mostly as post-hoc filters, treating behavioral constraints as fixed during repair. This formulation reduces repair to optimizing code under static and potentially misaligned constraints, leading to under-constrained search and brittle or overfitted fixes. We argue that repository-level issue resolution is fundamentally not optimization under fixed tests, but search over evolving behavioral constraints. To operationalize this view, we propose Agent-CoEvo, a coevolutionary multi-agent framework in which candidate code patches and test patches are jointly explored and iteratively refined. Rather than treating tests as immutable oracles, our framework models them as dynamic constraints that both guide and are revised by the repair process. Through mutual evaluation and semantic recombination, code and test candidates progressively narrow the space of behavior consistent with the issue description. Evaluated on SWE-bench Lite and SWT-bench Lite, Agent-CoEvo consistently outperforms state-of-the-art agent-based and agentless baselines in both repair success and test reproduction quality. Our findings suggest that enabling repair agents to revise behavioral constraints during search is critical for reliable issue resolution, pointing toward a shift from code-only optimization to coevolution of implementation and specification.
CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation
The Hong Kong Polytechnic University（香港理工大学）；University of Edinburgh（爱丁堡大学）；UCL（伦敦大学学院）；CUHK (SZ)（香港中文大学（深圳））；SUTD（新加坡科技设计大学）；HKUST（香港科技大学）；CUHK（香港中文大学）；HKUST (GZ)（香港科技大学（广州））
Zero2Repo: Can Coding Agents Build Repositories from Scratch?
Gradient Data；McGill University（麦吉尔大学）；Carnegie Mellon University（卡内基梅隆大学）；University of The Cumberlands（坎伯兰大学）；Queen’s University（女王大学）；MIT（麻省理工学院）；University College London, University of London（伦敦大学学院）；University of California, San Diego（加州大学圣地亚哥分校）
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
Tencent（腾讯）；Indiana University（印第安纳大学）；University of Maryland, College Park（马里兰大学帕克分校）；University of Georgia（佐治亚大学）；National University of Singapore（新加坡国立大学）
