Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Paper • 2606.12344 • Published • 71
TerryPei
TerryPei
AI & ML interests
NLP
Recent Activity
upvoted a paper about 1 month ago
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks authored a paper over 2 years ago
LocalMamba: Visual State Space Model with Windowed Selective Scan authored a paper over 2 years ago
GPT Self-Supervision for a Better Data AnnotatorOrganizations
None yet