Skip to content
Preprint

GraphEvoResearcher: A Cost-Matched Mechanism Analysis of Explicit Reasoning Graphs in Training-Free Self-Reflection

Oct 2026 · 0 citations · 47 references
Computer Science

Abstract

Training-free self-reflective protocols (generate, critique, revise) improve LLM reasoning but operate on a flat token stream: revisions cannot identify which prior step is unreliable, and stopping cannot exploit structural convergence. We introduce GraphEvoResearcher, a training-free protocol that lifts EvoResearcher's self-reflective meta-reward onto an explicit reasoning graph whose nodes are intermediate conclusions and whose typed edges encode support, contradict, and depends_on, with a graph-aware reward over correctness, efficiency, reflection, diversity, and structural signals. On deepseek-chat over GSM8K, MATH, and BBH (n=50 each), the protocol reaches 98%, 92%, and 82% in about two calls per question. Gains are significant against single-shot decoding on GSM8K and MATH and against flat reflection only on MATH; against cost-matched self-consistency the protocol is competitive, not dominant. A paired mechanism ablation over a shared response cache then shows what the graph contributes: holding model outputs fixed, neither the structural stop rule nor contradiction-driven repair changes which item is answered correctly, so the gains come from the forced second pass rather than from the structural reward. The ablation exposes the reason: the answer step never reads the edges it builds. We fix this with an edge-consulting arbitration step, which repairs one BBH item and fires on only 4% of questions, locating the binding constraint in how often construction declares conflicts. Testing the implied prediction on HotpotQA (n=100) falsifies it: the trigger rate does not rise with mul

View source

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.