代码空间响应预言机：利用大语言模型生成可解释的多智能体策略
Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models
AI总结：
本文提出代码空间响应预言机，利用大语言模型生成可解释的多智能体策略，通过代码生成任务提升策略的可解释性和复杂策略发现能力。
摘要：
最近多智能体强化学习的进展，特别是策略空间响应预言机（PSRO），已使在日益复杂的领域中计算近似博弈论均衡成为可能。然而，这些方法依赖于深度强化学习预言机，生成的神经网络策略是
英文摘要：
Recent advances in multi-agent reinforcement learning, particularly Policy-Space Response Oracles (PSRO), have enabled the computation of approximate game-theoretic equilibria in increasingly complex domains. However, these methods rely on deep reinforcement learning oracles that produce `black-box' neural network policies, making them difficult to interpret, trust or debug. We introduce Code-Space Response Oracles (CSRO), a novel framework that addresses this challenge by replacing RL oracles with Large Language Models (LLMs). CSRO reframes the best response computation as a code generation task, prompting an LLM to generate policies directly as human-readable code. This approach not only yields inherently interpretable policies but also leverages the LLM's pretrained knowledge to discover complex, human-like strategies. We explore multiple ways to construct and enhance an LLM-based oracle: zero-shot prompting, iterative refinement and \emph{AlphaEvolve}, a distributed LLM-based evolutionary system. We demonstrate that CSRO achieves performance competitive with baselines while producing a diverse set of explainable policies. Our work presents a new perspective on multi-agent learning, shifting the focus from optimizing opaque policy parameters to synthesizing interpretable algorithmic behavior.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
