| title | Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models |
|---|---|
| authors | Dehai Min, Giovanni Vaccarino, Huiyi Chen, Yongliang Wu, Gal Yona, Lu Cheng |
| date | 2026-05-17 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.17672 |
| affiliation | University of Illinois Chicago |
| upvotes | 22 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Large Reasoning Models (LRMs) achieve strong performance by generating long chains of thought (CoT), but often overthink, continuing to reason after a solution has already stabilized and thereby wasting tokens and increasing latency. Existing inference-time early-exit methods rely primarily on answer-level signals, such as confidence or trial-answer consistency, to decide when to stop. However, these signals mainly reflect answer readiness rather than reasoning convergence: they may trigger before the model has finished exploring or self-correcting, causing premature exits that can degrade final-answer accuracy and leave the retained reasoning chain semantically incomplete. We identify reasoning-level semantic redundancy as a complementary signal for semantic-preserving early exit: when successive steps no longer add novel progress and instead revisit established conclusions, the reasoning trajectory has likely converged. Building on this insight, we propose PUMA, a plug-and-play framework that combines a lightweight Redundancy Detector with answer-level verification. The detector flags semantically redundant candidate exits, while verification confirms whether stopping is safe, allowing PUMA to remove redundant continuation while preserving both answer accuracy and a coherent reasoning prefix. Across five LRMs and five challenging reasoning benchmarks, PUMA achieves 26.2% average token reduction while preserving accuracy and retained CoT quality. Additional experiments on code generation, zero-shot vision-language reasoning, and learned stopping-policy internalization further demonstrate that reasoning-level redundancy is a robust, transferable, and learnable signal for efficient reasoning. Our code is available at https://github.com/giovanni-vaccarino/PUMA. |
cite
@misc{min2026stop,
title={Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models},
author={Dehai Min and Giovanni Vaccarino and Huiyi Chen and Yongliang Wu and Gal Yona and Lu Cheng},
year={2026},
eprint={2605.17672},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.17672}
}