Problem
Research questions and friction points this paper is trying to address.
Decentralized Agentic Reasoning
Centralized Protocols
Routing Bottlenecks
Static Role Allocations
Multimodal Queries
DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation
🤖 AI Summary
为解决复杂多模态查询处理中的瓶颈，提出DeAR框架，通过去中心化能力定位、思维导航和拓扑更新机制，实现自主协作，提高推理准确性。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Decentralized Agentic Reasoning
Capability Grounding
Thought Map Navigation
Topology Update
🔎 Similar Papers
