Overview

Large reasoning models study how language models can solve difficult problems by allocating computation across intermediate steps, tools, and alternative solution paths. Common approaches include reinforcement learning with verifiable rewards, supervised reasoning-trace distillation, tool use, search over sequential or parallel paths, and latent recurrent computation. Evaluation spans mathematics, coding, science question answering, logic, and multimodal tasks, measuring not only accuracy but also compute use, robustness, and the quality of intermediate reasoning. A central tension is that extra thinking can help on hard problems but also produce loops, errors, and safety risks, so researchers are developing adaptive stopping and compression while testing whether reasoning traces reliably reflect how answers are formed.

Latest papers

CardsList

349 papers8 papers in the last four weeks, down 74% on the four weeks before. 0.1% of all new papers.

  1. Reflection Steering: Disentangling Reflection from Reasoning in Activation Space for Token-Efficient Inference

    Aug 26, 2026Jiarui Hu, Zhiyuan Wen, Xiaoyun Liu +2Language Model SteeringEfficient Language Model Reasoning

  2. Parason: Revealing Subtask and Trial Parallelism in LLM Reasoning

    Aug 25, 2026Zhengyang Zhang, Zijian Zhang, Jiaxuan Gao +4Parallel Reasoning in Language ModelsEfficient Language Model Reasoning

  3. TRACE: An Evidence-Grounded Benchmark for Safety Evaluation of Large Reasoning Models

    Aug 25, 2026Zhenyu Wu, Siyuan Chen, Changchun Yang +8LLM Safety BenchmarksLanguage Model Safety Evaluation

  4. Cognitive Profiling of LRMs' Reasoning Traces Using Bloom's Taxonomy

    Aug 24, 2026Maria-Eleni Zoumpoulidi, Georgios Paraskevopoulos, Alexandros PotamianosLarge Reasoning ModelsReasoning Trace Analysis

  5. EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models

    Aug 20, 2026Yiting Qu, Ziqing Yang, Chi Cui +3LLM SecurityModel Extraction Attacks

  6. The IOL-AI Challenge: An Open Challenge towards Advancing Linguistic Reasoning

    Aug 18, 2026Eduardo Sánchez, Rita Berrada, Dan-Mircea Mirea +8Inductive Reasoning in Language ModelsLLM Reasoning

  7. ParaTempo: Efficient Parallel Reasoning via Temporal Confidence

    Aug 17, 2026Xuteng Zhang, Wenhao Zeng, Xiaodong Gu +5Parallel Reasoning in Language ModelsEfficient Language Model Reasoning

  8. Alignment of LRMs via Counter-Aligned Few-Shot Conversation Exposure

    Aug 16, 2026Xiangyu Zhou, Saleh Zare Zade, Dongxiao ZhuLLM AlignmentAdversarial Attacks on LLMs

  9. KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving

    Aug 16, 2026Minsoo Cheong, Woosang Lim, Vincent-Daniel Yun +1KV-Cache EvictionEfficient Language Model Inference

  10. Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models

    Aug 13, 2026Jean de Dieu Nyandwi, Leena Mathur, Yonatan Bisk +2Large Reasoning ModelsMetacognition in Language Models

  11. ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling

    Aug 11, 2026Vaibhav Singh, Soumya Suvra Ghosal, Sarvesh Gharat +3Numerical Reasoning in Language ModelsRetrieval-Augmented Reasoning

  12. Thought-Level Beam Search for Reasoning

    Aug 8, 2026Lijie Yang, Hongyin Luo, Jiawei Zhao +2Inference-Time SearchEfficient Language Model Reasoning

  13. Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions

    Aug 8, 2026Chenrui Fan, Yize Cheng, Ming Li +3LLM EvaluationInference-Time Compute Allocation

  14. REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment

    Aug 8, 2026Zhengze Huang, Luyang Yu, Di Hong +5LLM Hallucination MitigationLLM Reliability

  15. Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking

    Aug 7, 2026Devin Pereira, Willem ZuidemaLLM World ModelsLLM Planning

  16. Hierarchical Latent Prediction for Language Models

    Aug 6, 2026Chang Shi, Tim Pearce, Manan Tomar +2Language Model PretrainingMulti-Token Prediction

  17. Rewarding Efficient Reasoning Improves Abstention on Underspecified Tasks in Reasoning Models

    Aug 5, 2026Polina Tsvilodub, Max Höth, Michael Franke +2LLM AbstentionLarge Reasoning Models

  18. Same Formulas, Different Semantics: Do Language Models Follow Modal Logic Specifications?

    Aug 5, 2026Réemi Andrieu, Damien SileoLogical ReasoningLLM Evaluation

  19. Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning

    Aug 5, 2026Qiyuan Zhu, Dezhi Li, Pengyu Cheng +8Overthinking in Language ModelsKV Caching

  20. Evaluating Theory of Mind in Reasoning Models: Robustness over Reasoning

    Aug 5, 2026Ian B. de Haan, Peter van der Putten, Max van DuijnLLM EvaluationTheory of Mind

  21. Risky Business: Measuring The Faithfulness-Safety Tension

    Aug 4, 2026Dominik Meier, Luca Joshua Francis, Marco Bernhard Kaiser +3CoT FaithfulnessLanguage Model Safety Evaluation

  22. Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models

    Jul 30, 2026Sara Candussio, Daniel Scalena, Luca Bortolussi +3CoT CompressionLarge Reasoning Models