做AI协作系统或人机交互研究的团队值得关注——Co-pi-tree用可解释的策略树替代黑箱模型，既提升性能又大幅降低推理成本，实验数据很有说服力。
研究者提出Collaboration Policy Tree (Co-pi-tree)，一种将大语言模型推理蒸馏为可执行策略树的方法，用于人机协作。该方法包含伙伴行为预测树和智能体动作选择树，通过闭环交互反馈自动改进策略分支。在Overcooked-AI实验中，Co-pi-tree相比基线平均奖励提升35.4%，同时将LLM查询次数减少77.7%，测试延迟降低97.1%。这解决了传统多智能体强化学习缺乏可解释性、以及直接使用LLM决策成本高的问题。
Distilling LLM Reasoning into an Interpretable Policy Tree for Human-AI Collaboration
Constructing efficient and reliable policies to assist humans is indispensable for human-AI collaboration. Existing methods mainly follow two lines of work. Most prior work relies on multi-agent reinforcement learning (MARL) to learn black-box policies, which limits interpretability and raises safety concerns. Recent methods query large language models (LLMs) at each decision step, causing slow responses and high inference costs. We propose Collaboration Policy Tree (Co-pi-tree), a closed-loop method that learns an executable policy tree consisting of a partner-behavior prediction tree and an agent-action selection tree. Co-pi-tree constructs a policy by distilling LLM reasoning into policy tree code. It then evaluates the policy through partner interaction, obtains feedback, and uses natural language to summarize the interaction feedback to improve problematic branches. Experiments in Overcooked-AI show that Co-pi-tree improves average reward by 35.4% over the baseline average, while reducing the number of LLM queries by 77.7% and test-time latency by 97.1%. Project page: https://beiwenzhang.github.io/Co-pi-tree/