用多个不同语言模型协作，让AI规划更高效多样。
SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly
- 让多个异构语言模型协同决策，提升搜索多样性。
- 在多个基准任务上表现超越现有最优方法。
- 可部署在普通电脑，适合资源有限的场景。
近期研究日益关注利用大语言模型（LLMs）构建自主代理以解决复杂问题。然而，现有方法大多采用单代理框架，在蒙特卡洛树搜索（MCTS）中生成搜索分支并估算奖励，这种单代理范式天然限制了探索能力，导致生成分支多样性不足，规划性能欠佳。为此，我们提出协同多代理规划框架SYMPHONY，通过整合一组异构语言模型驱动的代理，利用各代理间不同的推理模式，增强回溯路径多样性，促进更有效的探索。在多个基准任务上的实证结果表明，即使使用可部署于消费级硬件的开源LLMs，SYMPHONY仍表现出色；当结合可通过API访问的云端LLMs时，性能进一步提升，超越现有最先进基线，验证了异构多代理协作在规划任务中的有效性。
原文摘要 · Abstract (English)
Recent advancements have increasingly focused on leveraging large language models (LLMs) to construct autonomous agents for complex problem-solving tasks. However, existing approaches predominantly employ a single-agent framework to generate search branches and estimate rewards during Monte Carlo Tree Search (MCTS) planning. This single-agent paradigm inherently limits exploration capabilities, often resulting in insufficient diversity among generated branches and suboptimal planning performance. To overcome these limitations, we propose Synergistic Multi-agent Planning with Heterogeneous langauge model assembly (SYMPHONY), a novel multi-agent planning framework that integrates a pool of heterogeneous language model-based agents. By leveraging diverse reasoning patterns across agents, SYMPHONY enhances rollout diversity and facilitates more effective exploration. Empirical results across multiple benchmark tasks show that SYMPHONY achieves strong performance even when instantiated with open-source LLMs deployable on consumer-grade hardware. When enhanced with cloud-based LLMs accessible via API, SYMPHONY demonstrates further improvements, outperforming existing state-of-the-art baselines and underscoring the effectiveness of heterogeneous multi-agent coordination in planning tasks.
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。