Early Stopping for Language Model Reasoning

Latest papers

22 papers5 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Is Token Confidence Just Chain Length? A Signal-Processing Audit of Reasoning Traces
Oct 27, 2026Pragna MallappaLLM Reasoning Language Model Reasoning Evaluation
Keshav Memorial Institute of Technology
Same Beliefs, Different Policies: Learning Reusable Representations for Early Stopping in LLM Reasoning
Oct 21, 2026Jingwei Ni, Dmitry Abulkhanov, Vladislav Smirnov +5Early Stopping for Language Model Reasoning Early Stopping
ETH Zürich · MBZUAI · University of Zürich +1
Adaptive Stopping of Streamed Reasoning for Language Model Agents
Oct 20, 2026JunHyeok Oh, Byung-Jun LeeEarly Stopping for Language Model Reasoning Adaptive Reasoning in Language Models
Korea University
Calibration-Free Early Stopping for Chain-of-Thought Reasoning via E-processes
Oct 18, 2026Dong-Jae Lee, Gyojin Han, Junmo KimEarly Stopping for Language Model Reasoning Adaptive Reasoning in Language Models
KAIST
Settle: Learning When to Stop Reasoning
Sep 30, 2026Ryan Brown, Zihao Fu, Chris RussellEarly Stopping for Language Model Reasoning Efficient Language Model Reasoning
Oxford Internet Institute, University of Oxford · Department of Linguistics and Modern Languages, The Chinese University of Hong Kong
The Model Knows When to Stop: Training-Free Early Stopping for Long-Context Reading
Sep 28, 2026Muath Alyobi, Mohamed Eltahir, Almoayyad Abuljdail +3Early Stopping Long-Context Language Model Evaluation
King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia · Department of Computer Science, Edge Hill University, Ormskirk, England
Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal
Sep 9, 2026Yunxiang Mo, Donghao Zhao, Hejia GengEarly Stopping LLM Reliability
HKUST · University of Oxford
</think> Doesn't Stop Reasoning: Analysis of Spurious CoT Termination
Sep 3, 2026Seunghee Koh, Sungjae Choi, Minchan Kwon +2CoT Reasoning Efficient Language Model Reasoning
Korea Advanced Institute of Science and Technology, South Korea
SABER: Stability-Aware Early Exit for LLM Reasoning via Adversarial Branch Probing
Aug 28, 2026Wanli Cheng, Haiya Xiang, Juntao Li +2Efficient Language Model Reasoning Early Stopping for Language Model Reasoning
Soochow University, China
BLADE: Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning
Jul 31, 2026Keshu Fu, Keqin Peng, Jun Bai +6Efficient Language Model Reasoning Efficient Language Model Inference
School of Computer Science and Engineering, Beihang University · Beijing Institute for General Artificial Intelligence, BIGAI · Academy for Advanced Interdisciplinary Studies, Peking University +1
UPAIR: Diagnosing Reasoning States via Uncertainty-Progress Alignment for Selective Intervention
Jul 19, 2026Cheng Yan, Zhijun Fan, Guangyang Ye +4Adaptive Inference Overthinking in Language Models
University of Science and Technology of China · AWS Agentic AI
OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping
Jul 13, 2026Mohammed Ehab, Aymane El Gadarri, Vivek F. Farias +2Efficient Language Model Reasoning Sequential Decision Making
MIT · Columbia Business School
When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models
Jun 29, 2026Zhe Dong, Fang Qin, Manish ShahEfficient Language Model Reasoning Cost-Aware Inference
University of Maine at Presque Isle · Stanford University · Independent Researcher
Stop When Further Reasoning Won't Help: Attention-State Adaptive Generation in Reasoning Models
Jun 13, 2026Jiakai Li, Ke Qin, Rongzheng Wang +4Early Stopping for Language Model Reasoning Efficient Language Model Inference
University of Electronic Science and Technology of China, Chengdu, China · Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province, Chengdu, China
ESPO: Early-Stopping Proximal Policy Optimization
May 28, 2026Zihang Li, Rui Zhou, Yingcheng Shi +8LLM Reasoning Reinforcement Learning
1Tongyi Lab , Alibaba Group · 2Peking University
Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models
May 17, 2026Dehai Min, Giovanni Vaccarino, Huiyi Chen +3Large Reasoning Models CoT Reasoning
University of Illinois Chicago · Politecnico di Milano · University of Illinois Urbana-Champaign +1
Large Language Models Decide Early and Explain Later
Apr 24, 2026Ayan Datta, Zhixue Zhao, Bhuvanesh Verma +3Efficient Language Model Reasoning LLM Inference Acceleration
IIIT Hyderabad · University of Sheffield, UK · Goethe University, Frankfurt am Main, Germany
TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping
Apr 22, 2026Yannis Belkhiter, Seshu Tirupathi, Giulio Zizzo +1Reasoning Trace Analysis Early Stopping
IBM Research Europe · Trinity College Dublin · Dublin, Ireland +1
Early Stopping for Large Reasoning Models via Confidence Dynamics
Apr 6, 2026Parsa Hosseini, Sumit Nawathe, Mahdi Salmani +2Early Stopping for Language Model Reasoning Early Stopping
University of Maryland · University of Southern California
ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention
Mar 23, 2026Xinyan Wang, Xiaogeng Liu, Ming Pei +1Early Stopping for Language Model Reasoning Overthinking in Language Models
University of Wisconsin–Madison · Johns Hopkins University
TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
Mar 13, 2026Alliot Nagle, Jakhongir Saydaliev, Dhia Garbaya +3Early Stopping for Language Model Reasoning Efficient Language Model Inference
UT Austin · EPFL · ENS Paris-Saclay +1
Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring
Dec 16, 2025Yannis Belkhiter, Seshu Tirupathi, Giulio Zizzo +1Reasoning Trace Analysis Efficient Language Model Reasoning
1IBM Research Europe, Dublin, Ireland · 2Trinity College Dublin, Ireland · 3ADAPT Research Centre, Dublin, Ireland

Oct 27, 2026J/K move · Enter open · S save

Is Token Confidence Just Chain Length? A Signal-Processing Audit of Reasoning Traces

Pragna Mallappa

Keshav Memorial Institute of Technology

LLM Reasoning Language Model Reasoning Evaluation Confidence Estimation in Language Models Early Stopping for Language Model Reasoning

Open paper AskPDF arXiv

Reasoning language models answer math problems by writing long chains of thought, and sampling many chains per problem and taking a majority vote raises accuracy at a large cost in generated text. A popular way to cut that cost scores each chain by the model's confidence in each token it writes, where a token is a word or part of a word. The method averages this confidence over a sliding window of 2048 tokens and keeps or stops chains based on the lowest average. We treat the confidence, recorded token by token, as a signal in the sense of audio or radio, and examine the method with standard signal-processing tools such as spectral analysis and statistical tests for detecting a sudden change. We sampled 16 chains for each of 500 problems from two math benchmarks with a small open reasoning model. The windowed-minimum score turns out to measure mostly how long a chain is. Ranking chains by length alone does as well as or better than the confidence score, and once length is accounted for the score carries no information about correctness. Signal processing explains why: the minimum of a longer stretch of a slowly drifting signal is lower by chance alone, and the confidence signal drifts slowly enough that this effect dominates. The spectrum does hold a small signal that length does not explain, since incorrect chains carry more rapid token-to-token fluctuation, but it is too weak to improve the vote. For stopping chains early, neither the sliding average nor a classical change detector beats the simpler choice of sampling fewer chains.