多智能体协作框架让AI能自适应推理与时间规划。
MACI: Multi-Agent Collaborative Intelligence for Adaptive Reasoning and Temporal Planning
- 用元规划器生成任务角色、约束和依赖图，加入常识增强
- 多智能体分工协作，运行时监控动态调整计划
- 适合复杂调度任务，提升AI的逻辑与时间管理能力
人工智能需要严谨推理、时间意识和有效约束管理，但传统大模型依赖模式匹配，缺乏自我验证和一致的约束处理能力。我们提出多智能体协作智能（MACI）框架，包含三个核心组件：1）元规划器（MP），能识别、构建并优化任务（如婚礼策划）的角色与约束，生成依赖图，并通过常识增强确保约束合理可行；2）一组智能体协同完成特定任务需求；3）运行时监控器，根据情况动态调整计划。通过解耦规划与验证、保持最小化智能体上下文并融合常识推理，MACI在两个调度问题中表现出鲁棒性能。
原文摘要 · Abstract (English)
Artificial intelligence requires deliberate reasoning, temporal awareness, and effective constraint management, capabilities traditional LLMs often lack due to their reliance on pattern matching, limited self-verification, and inconsistent constraint handling. We introduce Multi-Agent Collaborative Intelligence (MACI), a framework comprising three key components: 1) a meta-planner (MP) that identifies, formulates, and refines all roles and constraints of a task (e.g., wedding planning) while generating a dependency graph, with common-sense augmentation to ensure realistic and practical constraints; 2) a collection of agents to facilitate planning and address task-specific requirements; and 3) a run-time monitor that manages plan adjustments as needed. By decoupling planning from validation, maintaining minimal agent context, and integrating common-sense reasoning, MACI overcomes the aforementioned limitations and demonstrates robust performance in two scheduling problems.
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。