AI RESEARCH
Reasoning Graphs: Deterministic Agent Accuracy through Evidence-Centric Chain-of-Thought Feedback
arXiv CS.CL
•
ArXi:2604.07595v1 Announce Type: cross Language model agents reason from scratch on every query: each time an agent retrieves evidence and deliberates, the chain of thought is discarded and the next similar query starts with no prior insight. This produces lower accuracy and high variance, as the same type of query can succeed or fail unpredictably. We