SOURCE-LINKED INTELLIGENCE

Escaping Redundant Reasoning: Structure-Aware Search for Inference-Time LLMs

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Inference-time search with large language models (LLMs) often concentrates on a small set of structurally or semantically similar trajectories, leaving alternatives underexplored---a failure mode we call \textit{reasoning basin collapse}. We introduce BASIN, a training-free, structure-aware selection method that groups reasoning states into basins and penalizes repeated visits to the same strategy, thereby reallocating search across genuinely distinct reasoning paths under a fixed compute budget. Under matched inference budgets, BASIN improves over Tree of Thoughts (ToT) by up to $+22$pp on Ga

Read original source ↗ Open in workspace

recordType

paper

region

Global