Maintain agent-eval cases, judges, records, traces, campaigns, comparisons, and releases.
원문 언어: 영어
메뉴
SkillsMP는 tangle-network/agent-eval에서 5개의 skill을 수집했습니다. skill을 열어 소스와 세부 정보를 확인하세요.
수집된 skill 5개 중 5개를 표시합니다.
Maintain agent-eval cases, judges, records, traces, campaigns, comparisons, and releases.
원문 언어: 영어
Parse classic SWE-agent .traj trajectories: one step per entry of the trajectory array, in order, matching the CodeTraceBench annotation convention. No upstream CodeTracer commit ships a SWE-agent parser.
원문 언어: 영어
Parse OpenHands trajectories published as per-call LiteLLM completion logs (<model>-<timestamp>.json files with messages/response/kwargs/cost), the layout of CodeTraceBench's swe_raw OpenHands trials. Reads the call file whose messages hold the most tool-call…
원문 언어: 영어
Parse OpenHands session-event trajectories at the CodeTraceBench annotation granularity: one step per action event with a cause-paired observation (run, run_ipython, read, edit, think, recall). Outranks the seed openhands skill, which counts only…
원문 언어: 영어
Parse Terminus2 trajectories at command granularity: one step per entry of each episode response's commands array, matching the CodeTraceBench annotation convention. Outranks the seed terminus2 skill, whose episode-level steps do not align with the…
원문 언어: 영어