★ 47 +13 ⑂ 7 Python Apache-2.0 新项目 63
Simreal-AI/Simreal-MLBench
Innovative externally-scored agentic ML benchmark for next evolution of AI — real competition ground truth, two-submission feedback, attacked rewards
创建于 2026-09-21 · 最近推送 2026-09-23 · 首次出现在推荐 2026-09-23
agenticbenchmarkbenchmarkingcalibrationllmllm-agentsllmsmechine-learingmetacognition-in-llmsrl-environmentrsi
兴趣：multi-agent systems and LLM agents