Efficient Language Model Reasoning

Ask about this topic

Overview

This field asks how language models can solve tasks such as math, coding, science questions, and multi-hop retrieval without spending unnecessary computation. Common approaches compress or prune chain-of-thought, stop generation when answers stabilize, and adapt reasoning budgets to task difficulty; others use reinforcement learning, distillation, search, parallel sampling, or smaller-model routing. Newer work also explores latent reasoning and memory or KV-cache management to reduce the cost of generating and retaining explicit thoughts. The central tension is that extra reasoning can help on difficult problems but may waste resources, introduce errors, or even hurt accuracy, so methods are judged by both quality and cost on benchmarks such as GSM8K, MATH, AIME, and GPQA.

Latest papers

CardsList

373 papers89 papers in the last four weeks, up 218% on the four weeks before. 0.5% of all new papers.

  1. ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning

    Apr 7, 2026Xuan Xiong, Huan Liu, Li Gu +4Efficient Language Model ReasoningCoT Reasoning

    University of Toronto · McMaster University · Concordia University +1

  2. Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents

    Apr 6, 2026Neharika Jali, Anupam Nayak, Gauri JoshiMulti-Turn Language Model ReasoningEfficient Language Model Reasoning

    Carnegie Mellon University

  3. Early Stopping for Large Reasoning Models via Confidence Dynamics

    Apr 6, 2026Parsa Hosseini, Sumit Nawathe, Mahdi Salmani +2Early Stopping for Language Model ReasoningEarly Stopping

    University of Maryland · University of Southern California

  4. QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

    Apr 6, 2026LM-Provers, Yuxiao Qu, Amrith Setlur +6Mathematical ReasoningLLM Mathematical Reasoning

    CMU · Hugging Face · ETH Zurich +1

  5. Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents

    Apr 5, 2026Paulo Akira F. EnabeTool-Using Language AgentsLLM Agents

    Escola Politénica, University of São Paulo

  6. LightThinker++: From Reasoning Compression to Memory Management

    Apr 4, 2026Yuqi Zhu, Jintian Zhang, Zhenjie Wan +7Memory Management for LLM AgentsEfficient Language Model Reasoning

    Zhejiang University · Ant Group

  7. NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons

    Apr 3, 2026Haonan Dong, Kehan Jiang, Haoran Ye +3Large Reasoning ModelsEfficient Language Model Reasoning

    State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · School of Software and Microelectronics, Peking University

  8. FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models

    Apr 3, 2026Kehan Jiang, Haonan Dong, Zhaolu Kang +2Efficient Language Model ReasoningLarge Reasoning Models

    School of Software and Microelectronics, Peking University · State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University

  9. Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy

    Apr 3, 2026Yihong Dong, Jianha Xiao, Xue Jiang +7LLM EvaluationEfficient Language Model Reasoning

    Peking University, China · Wuhan University, China

  10. Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning

    Apr 2, 2026Bangji Yang, Hongbo Ma, Jiajun Fan +1Efficient Language Model ReasoningEfficient Language Model Inference

    University of Illinois Urbana-Champaign · Tsinghua University

  11. Brief Is Better: Non-Monotonic Chain-of-Thought Budget Effects in Function-Calling Language Agents

    Apr 2, 2026Xuan QiEfficient Language Model ReasoningLLM Agent Reliability

    IIIS, Tsinghua University

  12. Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning

    Apr 2, 2026Rafael Pardinas, Ehsan Kamalloo, David Vazquez +1LLM Inference EfficiencyRL for Language Model Reasoning

    ServiceNow AI Research

  13. On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning

    Apr 2, 2026Zhaoyi Li, Xiangyu Xi, Zhengyu Chen +6Supervised Fine-TuningEfficient Language Model Reasoning

    University of Science and Technology of China · Meituan LongCat Team · City University of Hong Kong +1

  14. ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models

    Apr 2, 2026Delip Rao, Feijiang Han, Chris Callison-BurchClaim VerificationLLM Answer Verification

    University of Pennsylvania, Philadelphia, PA, USA

  15. Adaptive Stopping for Multi-Turn LLM Reasoning

    Apr 1, 2026Xiaofan Zhou, Huy Nguyen, Bo Yu +2Multi-Turn Language Model ReasoningEfficient Language Model Reasoning

    Department of Computer Science, University of Illinois Chicago, Chicago, IL 60607, USA · Data science, Augustana College, Rock Island, IL 61201, USA · Department of Civil and Environmental Engineering, University of Utah, Salt Lake City, UT 84112, USA

  16. Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning

    Apr 1, 2026Cai Zhou, Zekai Wang, Menghua Wu +6Conformal Prediction for Language ModelsLanguage Model Calibration

    Department of Electrical Engineering and Computer Science (MIT EECS) · Computer Science and Artificial Intelligence Laboratory (MIT CSAIL) · Laboratory for Information and Decision Systems (MIT LIDS) +1

  17. Hierarchical Chain-of-Thought: Enhancing LLM Reasoning Performance and Efficiency

    Mar 31, 2026Xingshuai Huang, Derek Li, Bahareh Nikpour +1CoT ReasoningLLM Reasoning

    Huawei Technologies Canada, Canada · Huawei Noah’s Ark Lab, Canada

  18. Think Anywhere in Code Generation

    Mar 31, 2026Xue Jiang, Tianyu Zhang, Ge Li +8LLM Code GenerationEfficient Language Model Reasoning

    School of Computer Science, Peking University · Tongyi Lab, Alibaba Group

  19. CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning

    Mar 30, 2026Siyuan Ma, Bo Gao, Zikai Xiao +6Efficient Language Model ReasoningMetacognition in Language Models

    Nanyang Technological University · Carnegie Mellon University · Zhejiang University +5

  20. Avoiding Overthinking and Underthinking: Curriculum-Aware Budget Scheduling for LLMs

    Mar 29, 2026Amirul Rahman, Aisha Karim, Kenji Nakamura +1Efficient Language Model ReasoningInference-Time Compute Allocation

    University of Malaya

  21. Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models

    Mar 25, 2026Isha Puri, Mehul Damani, Idan Shenfeld +3RL for Language Model ReasoningEfficient Language Model Reasoning

    Massachusetts Institute of Technology

  22. Caterpillar of Thoughts: The Optimal Test-Time Algorithm for Large Language Models

    Mar 24, 2026Amir Azarmehr, Soheil Behnezhad, Alma GhafariInference-Time OptimizationEfficient Language Model Reasoning

    Northeastern University

  23. ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention

    Mar 23, 2026Xinyan Wang, Xiaogeng Liu, Ming Pei +1Early Stopping for Language Model ReasoningOverthinking in Language Models

    University of Wisconsin–Madison · Johns Hopkins University

  24. Data-Free Layer-Adaptive Merging via Fisher Information for Long-to-Short Reasoning LLMs

    Mar 23, 2026Tian XiaLanguage Model MergingModel Merging

  25. Reasoning Topology Matters: Network-of-Thought for Complex Reasoning Tasks

    Mar 21, 2026Fan HuangLLM ReasoningLLM Reasoning with Graphs

    Indiana University Bloomington

  26. The Y\mathbf{Y}-Combinator for LLMs: Solving Long-Context Rot with λλ-Calculus

    Mar 20, 2026Amartya Roy, Rasul Tutunov, Xiaotong Ji +2Long-Context Reasoning in Language ModelsLong-Context Language Model Inference

    The School of Interdisciplinary Research, Indian Institute of Technology (IIT) Delhi, Robert Bosch GmbH, India · Huawei Noah’s Ark Lab · Huawei Noah’s Ark +1

  27. LoopRPT: Reinforcement Pre-Training for Looped Language Models

    Mar 20, 2026Guo Tang, Shixin Jiang, Heng Chang +7Efficient Language Model ReasoningImplicit Reasoning in Language Models

    Harbin Institute of Technology, Harbin, China · Tsinghua University, Beijing, China · The Hong Kong University of Science and Technology, Guangzhou, China

  28. HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning

    Mar 20, 2026Beibei Xu, Yutong Ye, Chuyun Shen +3Agentic WorkflowsLLM Agent Workflow Optimization

    East China Normal University · Beihang University · Shanghai University of International Business and Economics +1

  29. TextReasoningBench: Does Reasoning Really Improve Text Classification in Large Language Models?

    Mar 20, 2026Xinyu Guo, Yazhou Zhang, Jing QinLarge Language Model-Based Text ClassificationLLM Evaluation

    School of Computer Science and Technology, Tianjin University, China · School of Nursing, The Hong Kong Polytechnic University, HongKong

  30. Balancing the Reasoning Load: Difficulty-Differentiated Policy Optimization with Length Redistribution for Efficient and Robust Reinforcement Learning

    Mar 19, 2026Yinan Xia, Haotian Zhang, Huiming WangRL for Language Model ReasoningEfficient Language Model Reasoning

    Tianjin University · Kuaishou Technology