DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation
arXiv:2608.17282v1 Announce Type: new 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 specializ...
arXiv cs.AI
·Xing Wei, Changmeng Zheng, XiaoYong Wei, Xiufen Ye, Qing Li
·