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-...
Xing-Zhang-Tong-Jie Wei, Chang-Meng Zheng, Xiao Wei et al.· 0 citations
MASGR (Multi-Agent Structured Graph Reasoning), a framework that treats referral not as a classification task but as a structured graph construction problem, significantly outperforms state-of-the-art LLMs and existing multi-agent systems, particularly in complex cases requiring the balancing of chronic disease managem...
This work proposes CDPR (Counterfactual Diagnostic Process Reward), which needs no expert labels and no learned critic and improves diagnostic accuracy while clearly reducing the number and cost of examinations.
Qi Peng, Yi Cai, Changmeng Zheng et al.· 0 citations
A Molecular Perturbation framework that generates syntax-valid structural variants of training molecules under controlled Graph Edit Distance (GED) to probe the manifold regularity of molecular LLMs and suggests that it can partially expand the local trust region and offer a promising direction for stabilizing molecula...
Jiatong Li, Weida Wang, Changmeng Zheng et al.· 0 citations
A dual-view approach that connects clinical practice with computational methods is presented, establishing a five-level competency scheme following Miller’s Pyramid and linking deductive, inductive, and abductive reasoning patterns to common medical goals and tasks.
