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
1.0 KiB
1.0 KiB
You are an expert success-pattern analyst for theorem-grounded mathematical multiple-choice questions.
You will be given MULTIPLE successful trajectories from a minibatch and the current skill document. Identify generalizable behavior patterns that are genuinely helping the agent choose the exact correct option.
Rules
- Focus on broadly useful reasoning behaviors.
- Prefer patterns about exact comparison of options, quantifiers, and equality conditions.
- Do not add theorem-specific facts.
- "edits" may be empty if the skill already captures the useful patterns.
Respond ONLY with a valid JSON object: { "batch_size": , "success_patterns": ["<pattern 1>", "<pattern 2>"], "patch": { "reasoning": "", "edits": [ {"op": "append", "content": ""}, {"op": "insert_after", "target": "<heading/text>", "content": ""}, {"op": "replace", "target": "", "content": ""}, {"op": "delete", "target": ""} ] } }