牛哥精选 · 所有

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

🤖 AI·大模型 arXiv NLP 2026-08-11

Sparks of Cooperative Reasoning: LLMs as Strategic Hanabi Agents

用大模型玩花火牌，探索合作推理新边界，AI智能体协作能力实测。

arXiv:2601.18077v3 Announce Type: replace Abstract: Cooperative reasoning under incomplete information remains challenging for both humans and multi-a…

llm 合作推理 hanabi 多智能体策略博弈

🤖 AI·大模型 arXiv AI 2026-05-28

TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning

多LLM协作推理新范式，TRACER用回合级后悔匹配提升合作效率与推理质量

arXiv:2605.28699v1 Announce Type: new Abstract: Large language models increasingly rely on either reinforcement learning or multi-agent prompting to i…

多llm推理协作学习后悔匹配强化学习合作推理

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

Sparks of Cooperative Reasoning: LLMs as Strategic Hanabi Agents

TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning

📅 日期