多大模型协作搜索，提升复杂问题推理准确率
Multi-LLM Collaborative Search for Complex Problem Solving
- 多个大模型并行探索并迭代优化推理路径
- 在四个基准上显著优于单模型和现有多模型方法
- 特别擅长数学与常识类复杂推理任务
大语言模型（LLMs）在处理复杂推理任务时，常因推理空间广阔及自然语言固有的模糊性而受限。我们提出混合搜索代理（MoSA）范式，利用多个LLM的集体专长来增强基于搜索的推理能力。MoSA通过结合独立探索与多模型间的迭代优化，整合多样化推理路径，缓解单模型方法的局限性。以蒙特卡洛树搜索（MCTS）为骨架，MoSA使多个智能体共同提出并聚合推理步骤，从而提升准确性。我们在四个推理基准上的全面评估显示，MoSA在复杂数学与常识推理任务中持续优于单代理及其他多代理基线。
原文摘要 · Abstract (English)
Large language models (LLMs) often struggle with complex reasoning tasks due to their limitations in addressing the vast reasoning space and inherent ambiguities of natural language. We propose the Mixture-of-Search-Agents (MoSA) paradigm, a novel approach leveraging the collective expertise of multiple LLMs to enhance search-based reasoning. MoSA integrates diverse reasoning pathways by combining independent exploration with iterative refinement among LLMs, mitigating the limitations of single-model approaches. Using Monte Carlo Tree Search (MCTS) as a backbone, MoSA enables multiple agents to propose and aggregate reasoning steps, resulting in improved accuracy. Our comprehensive evaluation across four reasoning benchmarks demonstrates MoSA's consistent performance improvements over single-agent and other multi-agent baselines, particularly in complex mathematical and commonsense reasoning 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。