arXiv cs.AI
Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation
궤적 인지 평가를 통한 효율적인 SWE 에이전트 벤치마킹
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.