提出新框架让两个AI通过协作学习，显著提升多智能体任务表现。
ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration
- 采用基于强化学习的双代理架构，明确训练协作能力
- 在多个基准测试中超越当前最先进方法的表现
- 适合需要高效协同的复杂任务场景
大型语言模型（LLMs）在多种语言任务中展现出强大能力。近期研究显示，通过多模型间的迭代对话可提升性能。然而，现有方法将协作视为涌现行为，依赖预训练模型自带协作能力。为解决此问题，我们提出ACC-Collab，一种基于演员-评论家机制的学习框架，训练一对专用协作代理（演员代理与评论家代理）。实验表明，ACC-Collab在广泛基准测试中优于当前最先进的多智能体技术。
原文摘要 · Abstract (English)
Large language models (LLMs) have demonstrated a remarkable ability to serve as general-purpose tools for various language-based tasks. Recent works have demonstrated that the efficacy of such models can be improved through iterative dialog between multiple models. While these paradigms show promise in improving model efficacy, most works in this area treat collaboration as an emergent behavior, rather than a learned behavior. In doing so, current multi-agent frameworks rely on collaborative behaviors to have been sufficiently trained into off-the-shelf models. To address this limitation, we propose ACC-Collab, an Actor-Critic based learning framework to produce a two-agent team (an actor-agent and a critic-agent) specialized in collaboration. We demonstrate that ACC-Collab outperforms SotA multi-agent techniques on a wide array of benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。