CharlesYang030
244e346b83
- Skill optimization framework with training loop analogy - 11 benchmarks, 4 model backends (Azure OpenAI, Claude, Codex, Qwen) - WebUI for browser-based training control - Pluggable architecture for extending benchmarks and backends
1.2 KiB
You will be given several failed agent trajectories from one minibatch and the current skill document.
Summarize the lessons from these trajectories into one complete replacement skill document.
When rewriting from a minibatch, use the current trajectories as the primary evidence for updates. Preserve essential task-format instructions, but avoid mechanically carrying over stale, redundant, or conflicting rules. Prefer a concise, coherent replacement skill over a long document with weakly supported guidance.
Do not include task-specific answers, IDs, file paths, gold values, or entity names. If the skill contains a protected block between and
, keep that block unchanged.Respond ONLY with a valid JSON object: { "batch_size": , "failure_summary": [ {"failure_type": "", "count": , "description": ""} ], "patch": { "reasoning": "", "skill_candidates": [ { "title": "", "change_summary": ["<short change 1>", "<short change 2>"], "new_skill": "" } ] } }
Return exactly one item in "skill_candidates".