AI 中文总结
针对现有智能体推理系统的路由瓶颈与静态角色分配问题，提出DeAR框架，通过三种机制实现去中心化协作，在9类基准测试中性能优于基线方法，提升了知识密集型推理任务的准确性。
AI 中文摘要
现有的智能体推理系统通常依赖集中式协议，这种设计会引入路由瓶颈和静态角色分配，在处理复杂多模态查询时往往失效。我们提出DeAR（Decentralized Agentic Reasoning，去中心化智能体推理）框架，将模式从集中控制转变为自主点对点协作。DeAR建立在三种机制之上：（1）用于依赖查询的智能体专业化的去中心化能力锚定；（2）用于定向同伴交互的思维图导航；（3）用于自适应错误修正的拓扑更新。在9种不同的多模态推理和基于文本的问答基准上的评估表明，DeAR始终优于近期的基线方法，验证了智能体间去中心化自适应协作可提升知识密集型推理任务的准确性。源代码将在论文接受后于https://open_upon_acceptance公开。
英文摘要
Existing agentic reasoning systems typically rely on centralized protocols. This design introduces routing bottlenecks and static role allocations that often fail when handling complex multimodal queries. We propose DeAR (Decentralized Agentic Reasoning), a framework that shifts from central control to autonomous peer-to-peer collaboration. DeAR is built on three mechanisms: (1) decentralized capability grounding for query-dependent agent specialization, (2) thought map navigation for targeted peer interactions, and (3) topology update for adaptive error correction. Evaluations across 9 diverse multimodal reasoning and text-based QA benchmarks indicate that DeAR consistently outperforms recent baseline methods, validating that decentralized and adaptive collaboration among agents enhances accuracy in knowledge-intensive reasoning tasks. The source code will be available at https://open_upon_acceptance.
