{"ID":5439490,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-02T19:06:01.127452785Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.30852","arxiv_id":"2606.30852","title":"When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models","abstract":"Reasoning models spend different amounts of useful computation across instances, but it remains unclear when a learned stopping rule improves over simple confidence or convergence thresholds. We study this question with LearnStop, a hidden-state-free checkpoint stopper for reasoning language models. At fixed budget checkpoints, LearnStop probes a short answer from the current reasoning prefix and predicts prefix correctness from online features such as answer confidence, entropy, prefix vote share, answer stability, and backtracking-marker density. Across 18 task-model settings spanning GSM8K, MATH-500, MMLU-Pro, AIME-90, GPQA, Qwen3, and DeepSeek-R1 distillations, the answer is task-dependent. On free-form math, learned multi-feature stopping improves the fixed-budget frontier and often beats scalar exits: on GSM8K with Qwen3-32B, the empirical frontier reaches a post-hoc peak adapt gain of +0.157, validation-selected operating points preserve positive gains, and the paired gain over the strongest scalar baseline is +0.028. On multiple-choice and very hard settings, scalar confidence, entropy, or stability rules are competitive or stronger. We therefore frame learned stopping not as a universal replacement for scalar exits, but as a tool whose value depends on trajectory structure. We further provide validation-selected operating points, paired bootstrap tests, finite-grid lost-correct risk calibration, cost accounting under KV-fork, prefix-cache, and black-box regimes, H100 serving profiles, checkpoint-schedule sweeps, transfer analyses, and robustness checks. The main practical finding is that learned stopping is useful when many questions become correct before full budget but do not exhibit a single reliable scalar stopping signal; its benefits largely disappear when confidence or answer convergence already solves the stopping problem.","short_abstract":"Reasoning models spend different amounts of useful computation across instances, but it remains unclear when a learned stopping rule improves over simple confidence or convergence thresholds. We study this question with LearnStop, a hidden-state-free checkpoint stopper for reasoning language models. At fixed budget che...","url_abs":"https://arxiv.org/abs/2606.30852","url_pdf":"https://arxiv.org/pdf/2606.30852v1","authors":"[\"Zhe Dong\",\"Fang Qin\",\"Manish Shah\"]","published":"2026-06-29T19:33:42Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false}