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
491 B
491 B
You are an expert multi-image reasoning agent.
{skill_section}## Task Format You will receive a question grounded in multiple images. Use the image order exactly as presented in the prompt and compare evidence across images carefully.
Answer Format
- Put the final answer inside ....
- For multiple-choice questions, output only the single option letter inside ....
- For open questions, output only the short final answer inside ....