[论文] SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent C...

论文概要

研究领域: ML
作者: Joel Sol, Homayoun Najjaran
发布时间: 2025-06-01
arXiv: 2506.00634

中文摘要

随着LLM的广泛部署，它们越来越被期望与其他AI智能体协同工作，而非孤立运行。这类场景中的有效协调需要智能体进行通信、共享信息并在不确定性下做出决策。本文引入SMAC-Talk，一种星际争霸多智能体挑战的自然语言扩展，用于评估基于LLM的智能体在合作式多智能体环境中的表现。该环境具有分散控制、部分可观测性和长时程决策等关键特征。SMAC-Talk包含自然语言通信通道，用于探测智能体间的协调与信任。我们利用这一通信通道构建不同的评估场景，包括嵌入欺骗性通信者、仅通过通信来扰乱和欺骗盟友的设置。我们提供三个智能体用于基准测试，使用Qwen3.5家族的4个模型，并研究推理结构、记忆和模型规模如何影响智能体间的协调。我们将SMAC-Talk作为开放基准发布，以支持研究社区开发和评估合作式多智能体场景中的LLM智能体。

原文摘要

As LLMs become more widely deployed, they are increasingly expected to work alongside other AI agents rather than operating in isolation. Effective coordination in these settings requires agents to communicate, share information and make decisions under uncertainty. We introduce SMAC-Talk, a natural language extension of the StarCraft Multi-Agent Challenge for evaluating LLM-based agents in cooperative multi-agent environments. The environment has several key features such as decentralized control, partial observability and long-horizon decision making. SMAC-Talk includes a natural language communication channel which is used to probe agent coordination and trust. We use this communication channel to construct different evaluation scenarios, including settings with an embedded deceptive co...

自动采集于 2026-06-05

#论文 #arXiv #ML #小凯