迈向协作智能：利用大语言模型在多智能体协调中传播意图与推理
Towards Collaborative Intelligence: Propagating Intentions and Reasoning for Multi-Agent Coordination with Large Language Models
AI总结：
提出一个基于大语言模型的协作智能体框架，通过传播意图和动态规划，减少多智能体强化学习中的协调错误，实现涌现协调行为。
摘要：
在多智能体系统中，有效的协作要求智能体之间沟通目标和意图。当前的智能体框架常常受限于对单智能体执行的依赖，并且缺乏稳健的模块间通信，这经常导致多智能体强化学习（MARL）策略欠佳以及任务协调不足。为了应对这些挑战，我们提出一个框架，用于训练大语言模型（LLMs）作为协作智能体，以在协作式MARL中实现协调行为。每个智能体维护一个由当前目标和相关子任务组成的私有意图。智能体定期广播其意图，使其他智能体能够推断协调任务。一个传播网络将广播的意图转换为针对队友的通信消息，与指定的队友共享相关目标。我们框架的架构分为规划、落地和执行模块。在执行过程中，多个智能体在下游环境中交互并沟通意图以实现协调行为。落地模块根据出现的协调模式动态调整理解策略，而来自执行智能体的反馈影响规划模块，从而能够动态重新规划子任务。在协作环境模拟中的结果表明，意图传播通过对齐智能体之间的子任务依赖关系减少了协调错误。智能体学会何时沟通意图以及哪些队友需要任务细节，从而产生涌现的协调行为。这证明了基于LLMs的协作式多智能体强化学习中意图共享的有效性。
英文摘要：
Effective collaboration in multi-agent systems requires communicating goals and intentions between agents. Current agent frameworks often suffer from dependencies on single-agent execution and lack robust inter-module communication, frequently leading to suboptimal multi-agent reinforcement learning (MARL) policies and inadequate task coordination. To address these challenges, we present a framework for training large language models (LLMs) as collaborative agents to enable coordinated behaviors in cooperative MARL. Each agent maintains a private intention consisting of its current goal and associated sub-tasks. Agents broadcast their intentions periodically, allowing other agents to infer coordination tasks. A propagation network transforms broadcast intentions into teammate-specific communication messages, sharing relevant goals with designated teammates. The architecture of our framework is structured into planning, grounding, and execution modules. During execution, multiple agents interact in a downstream environment and communicate intentions to enable coordinated behaviors. The grounding module dynamically adapts comprehension strategies based on emerging coordination patterns, while feedback from execution agents influnces the planning module, enabling the dynamic re-planning of sub-tasks. Results in collaborative environment simulation demonstrate intention propagation reduces miscoordination errors by aligning sub-task dependencies between agents. Agents learn when to communicate intentions and which teammates require task details, resulting in emergent coordinated behaviors. This demonstrates the efficacy of intention sharing for cooperative multi-agent RL based on LLMs.
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。
