Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models
TL;DR
Two test-time monitoring strategies are proposed: reasoning expression monitoring and hidden states monitoring, that reduce token usage by 62.7-93.6%, substantially improving efficiency and reliability while largely preserving accuracy.
Abstract
Current answering paradigms for Large Reasoning Models (LRMs) often fail to account for the fact that some questions may lie beyond the model's operational capability boundary, leading to long but unproductive reasoning. In this paper, we study whether LRMs expose early signals predictive of such cases, and whether these signals can be used to mitigate unproductive reasoning. In black-box settings, we find that reasoning expressions contain failure-predictive signals. In white-box settings, we show that the hidden states of the last input token contain information that is predictive of whether a question will not be solved correctly under our evaluation setup. Building on these observations, we propose two test-time monitoring strategies: reasoning expression monitoring and hidden states monitoring, that reduce token usage by 62.7-93.6%, substantially improving efficiency and reliability while largely preserving accuracy.
