Story
arxiv_llm_reliability · Oct 5, 2026 · paper
Source brief
Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents
arxiv.orgOct 5, 2026
original source linked
In brief
Autonomous coding agents now resolve a substantial share of real-world GitHub issues. However, passing functional tests differs fundamentally from producing a high-quality contribution acceptable for merging. Mature o...
Feed lens
agentevaluation