让多个AI智能体动态协作，自动分工并竞争优化文档理解结果。
Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems
- 智能体根据信心和负载动态分配任务，灵活调整工作流程。
- 通过双向反馈与竞争机制，提升输出的准确性和连贯性。
- 适合复杂文档处理场景，尤其在开放性任务中表现更优。
大型语言模型（LLM）智能体在协同任务完成方面展现出巨大潜力。然而，现有多智能体框架通常依赖静态工作流、固定角色和有限的智能体间通信，在开放性、高复杂度领域效果受限。本文提出一种协调框架，通过三种核心机制实现适应性：动态任务路由、双向反馈以及并行智能体评估。该框架使智能体可根据置信度和工作负载重新分配任务，通过结构化批评迭代改进输出，并在高模糊性子任务上进行竞争，由评估器选择最优结果。我们在模块化架构中实现了这些原则，并在事实覆盖、连贯性和效率方面显著优于静态及部分自适应基线。研究结果表明，将适应性与结构化竞争结合对多智能体LLM系统具有显著优势。
原文摘要 · Abstract (English)
Large language model (LLM) agents have shown increasing promise for collaborative task completion. However, existing multi-agent frameworks often rely on static workflows, fixed roles, and limited inter-agent communication, reducing their effectiveness in open-ended, high-complexity domains. This paper proposes a coordination framework that enables adaptiveness through three core mechanisms: dynamic task routing, bidirectional feedback, and parallel agent evaluation. The framework allows agents to reallocate tasks based on confidence and workload, exchange structured critiques to iteratively improve outputs, and crucially compete on high-ambiguity subtasks with evaluator-driven selection of the most suitable result. We instantiate these principles in a modular architecture and demonstrate substantial improvements in factual coverage, coherence, and efficiency over static and partially adaptive baselines. Our findings highlight the benefits of incorporating both adaptiveness and structured competition in multi-agent LLM systems.
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。