HALO让多个AI智能体分层协作，自动规划任务并优化推理路径。
HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems
- 分三层架构：规划、角色生成、执行，实现动态协作
- 用蒙特卡洛树搜索找最优推理路径，提升任务完成率14.4%
- 适合需要复杂推理的专家级任务，尤其擅长道德判断和代数题
基于大语言模型的多智能体系统在多种任务中展现出巨大潜力，但现有系统通常依赖预设的角色设计和静态通信结构，限制了其在复杂交互环境中的适应性与灵活性，导致在高度专业化和专家级任务上表现不佳。为此，我们提出HALO，一种基于分层推理架构的多智能体协作框架。具体包括高层规划代理用于任务分解，中层角色设计代理用于子任务特定的智能体实例化，底层推理代理用于子任务执行。特别地，子任务执行被重构为结构化工作流搜索问题，利用蒙特卡洛树搜索（MCTS）系统探索智能体动作空间，构建最优推理轨迹。此外，针对多数用户缺乏提示工程能力的问题，引入自适应提示优化模块，将原始查询转化为任务特定提示。在代码生成（HumanEval）、通用推理（MMLU）和算术推理（MATH）基准数据集上的实证评估表明，HALO相比最先进基线平均提升14.4%。尤为显著的是，在MMLU的道德情景子集上最高提升13.3%，在MATH的代数子领域最高提升19.6%，体现了其在处理高度专业化和专家级任务上的卓越能力。代码已开源：https://github.com/23japhone/HALO。
原文摘要 · Abstract (English)
Recent advancements in Multi-Agent Systems (MAS) powered by Large Language Models (LLMs) have demonstrated tremendous potential in diverse task scenarios. Nonetheless, existing agentic systems typically rely on predefined agent-role design spaces and static communication structures, limiting their adaptability as well as flexibility in complex interaction environments and leading to subpar performance on highly specialized and expert-level tasks. To address these issues, we introduce HALO, a multi-agent collaboration framework based on a hierarchical reasoning architecture. Specifically, we incorporate a high-level planning agent for task decomposition, mid-level role-design agents for subtask-specific agent instantiation, and low-level inference agents for subtask execution. Particularly, subtask execution is reformulated as a structured workflow search problem, where Monte Carlo Tree Search (MCTS) systematically explores the agentic action space to construct optimal reasoning trajectories. Additionally, as the majority of users lack expertise in prompt engineering, we leverage an Adaptive Prompt Refinement module to transform raw queries into task-specific prompts. Empirical evaluations on Code Generation (HumanEval), General Reasoning (MMLU), and Arithmetic Reasoning (MATH) benchmark datasets highlight the effectiveness of HALO, yielding a 14.4% average improvement over state-of-the-art baselines. Notably, HALO achieves up to 13.3% performance gain on the Moral Scenarios subject in the MMLU benchmark and up to 19.6% performance gain on the Algebra subarea in the MATH benchmark, indicating its advanced proficiency in tackling highly specialized and expert-level tasks. The code repository is available at https://github.com/23japhone/HALO.
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。