Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning

摘要

Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating safety risks where plausible-sounding but incorrect derivations mislead users. We characterize this futile reasoning phenomenon through systematic analysis, revealing universal capability overreach and systematic miscalibration towards over-confidence. The dominant failure mode is specious reasoning, superficially valid outputs with subtle hallucinations, which escalates with task difficulty. We demonstrate that prompt engineering proves insufficient to calibrate refusal behavior. To address this, we introduce CaRL (Capability-aligned Reinforcement Learning), which aligns model behavior with capability boundaries through reward shaping that incentivizes refusal over hallucination and hindsight augmentation that converts failures into refusal supervision. Experiments demonstrate a substantial reduction in futile reasoning while preserving performance across task difficulties, effectively achieving capability-aligned behavior without sacrificing utility.