{"total":73,"rows":[{"id":"2502.05171","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","created":"2025-02-07","cited_by_count":415,"area":"lr"},{"id":"2507.01352","title":"Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy","created":"2025-07-02","cited_by_count":214,"area":"lr"},{"id":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210,"area":"lr"},{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2504.07912","title":"Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining","created":"2025-04-10","cited_by_count":129,"area":"lr"},{"id":"2507.16806","title":"Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty","created":"2025-07-22","cited_by_count":117,"area":"lr"},{"id":"2506.20512","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","created":"2025-06-25","cited_by_count":113,"area":"lr"},{"id":"2507.10532","title":"Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination","created":"2025-07-14","cited_by_count":82,"area":"lr"},{"id":"2507.14111","title":"CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning","created":"2025-07-18","cited_by_count":61,"area":"lr"},{"id":"2505.21318","title":"Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations","created":"2025-05-27","cited_by_count":49,"area":"lr"},{"id":"2511.07384","title":"Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence","created":"2025-11-10","cited_by_count":47,"area":"lr"},{"id":"2504.04022","title":"Rethinking Reflection in Pre-Training","created":"2025-04-05","cited_by_count":43,"area":"lr"},{"id":"2502.17407","title":"Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning","created":"2025-02-24","cited_by_count":37,"area":"lr"},{"id":"2507.11407","title":"EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes","created":"2025-07-15","cited_by_count":32,"area":"lr"},{"id":"2607.02234","title":"Purified OPSD: On-Policy Self-Distillation Without Losing How to Think","created":"2026-07-02","cited_by_count":31,"area":"lr"},{"id":"2510.07358","title":"Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts","created":"2025-10-08","cited_by_count":24,"area":"lr"},{"id":"2503.23084","title":"The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction","created":"2025-03-29","cited_by_count":21,"area":"lr"},{"id":"2510.10974","title":"Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning","created":"2025-10-13","cited_by_count":20,"area":"lr"},{"id":"2506.14948","title":"Structured Moral Reasoning in Language Models: A Value-Grounded Evaluation Framework","created":"2025-06-17","cited_by_count":16,"area":"lr"},{"id":"2507.10616","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them","created":"2025-07-13","cited_by_count":15,"area":"lr"},{"id":"2503.13447","title":"MetaScale: Test-Time Scaling with Evolving Meta-Thoughts","created":"2025-03-17","cited_by_count":13,"area":"lr"},{"id":"2505.21479","title":"Are Language Models Consequentialist or Deontological Moral Reasoners?","created":"2025-05-27","cited_by_count":12,"area":"lr"},{"id":"2504.07825","title":"Who Benchmarks the Benchmarks? Towards Comprehensive Evaluation of Commonsense Reasoning Benchmarks","created":"2025-04-10","cited_by_count":11,"area":"lr"},{"id":"2506.05850","title":"Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models","created":"2025-06-06","cited_by_count":11,"area":"lr"},{"id":"2506.12301","title":"Unveiling Confirmation Bias in Chain-of-Thought Reasoning","created":"2025-06-14","cited_by_count":10,"area":"lr"},{"id":"2510.04230","title":"Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought","created":"2025-10-05","cited_by_count":10,"area":"lr"},{"id":"2506.13331","title":"Mixture of Cognitive Reasoners: Modular Reasoning with Brain-Like Specialization","created":"2025-06-16","cited_by_count":9,"area":"lr"},{"id":"2506.02211","title":"Improving LLM-Generated Code Quality with GRPO","created":"2025-06-02","cited_by_count":8,"area":"lr"},{"id":"2506.22403","title":"HyperCLOVA X THINK Technical Report","created":"2025-06-27","cited_by_count":7,"area":"lr"},{"id":"2509.24945","title":"MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2509.24375","title":"Reinforcement Mid-Training","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2503.13661","title":"Pensez: Less Data, Better Reasoning -- Rethinking French LLM","created":"2025-03-17","cited_by_count":5,"area":"lr"},{"id":"2505.07293","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2509.21013","title":"Predicting LLM Reasoning Performance with Small Proxy Model","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2509.21499","title":"On Code-Induced Reasoning in LLMs","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2511.07833","title":"MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation","created":"2025-11-11","cited_by_count":5,"area":"lr"},{"id":"2607.16097","title":"Understanding Reasoning from Pretraining to Post-Training","created":"2026-07-17","cited_by_count":5,"area":"lr"},{"id":"2508.02037","title":"Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time","created":"2025-08-04","cited_by_count":4,"area":"lr"},{"id":"2509.21443","title":"One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning","created":"2025-09-25","cited_by_count":4,"area":"lr"},{"id":"2509.24653","title":"Unveiling the Mechanisms of Multi-Hop Reasoning in Transformers via Identity Bridge","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2510.07731","title":"oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning","created":"2025-10-09","cited_by_count":4,"area":"lr"},{"id":"2510.09426","title":"KORMo: Korean Open Reasoning Model for Everyone","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2602.14868","title":"Goldilocks RL: Tuning Task Difficulty to Escape Sparse Rewards for Reasoning","created":"2026-02-16","cited_by_count":4,"area":"lr"},{"id":"2605.07153","title":"Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"id":"2502.09042","title":"Typhoon T1: An Open Thai Reasoning Model","created":"2025-02-13","cited_by_count":3,"area":"lr"},{"id":"2504.16832","title":"GreenMind: A Next-Generation Vietnamese Large Language Model for Structured and Logical Reasoning","created":"2025-04-23","cited_by_count":3,"area":"lr"},{"id":"2504.18225","title":"Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family","created":"2025-04-25","cited_by_count":3,"area":"lr"},{"id":"2509.11026","title":"Rethinking Human Preference Evaluation of LLM Rationales","created":"2025-09-14","cited_by_count":3,"area":"lr"},{"id":"2511.03808","title":"Optimizing Reasoning Efficiency through Prompt Difficulty Prediction","created":"2025-11-05","cited_by_count":3,"area":"lr"},{"id":"2602.16085","title":"Language Statistics and False Belief Reasoning: Evidence from 41 Open-Weight LMs","created":"2026-02-17","cited_by_count":3,"area":"lr"},{"id":"2604.04944","title":"Inclusion-of-Thoughts: Mitigating Preference Instability via Purifying the Decision Space","created":"2026-03-15","cited_by_count":3,"area":"lr"},{"id":"2605.23315","title":"Convergence Without Understanding: When Language Models Agree on Representations but Disagree on Reasoning","created":"2026-05-22","cited_by_count":3,"area":"lr"},{"id":"2502.11573","title":"InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2506.02481","title":"Do Language Models Think Consistently? A Study of Value Preferences Across Varying Response Lengths","created":"2025-06-03","cited_by_count":2,"area":"lr"},{"id":"2507.17442","title":"Confident RAG: Enhancing the Performance of LLMs for Mathematics Question Answering through Multi-Embedding and Confidence Scoring","created":"2025-07-23","cited_by_count":2,"area":"lr"},{"id":"2509.20866","title":"On the Robustness of Answer Formats in Medical Reasoning Models","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2510.24256","title":"From Memorization to Reasoning in the Spectrum of Loss Curvature","created":"2025-10-28","cited_by_count":2,"area":"lr"},{"id":"2508.18672","title":"Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2603.09205","title":"Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2603.20219","title":"Thinking into the Future: Latent Lookahead Training for Transformers","created":"2026-03-03","cited_by_count":1,"area":"lr"},{"id":"2607.27919","title":"Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2511.10381","title":"Position: On the Methodological Pitfalls of Evaluating Base LLMs for Reasoning","created":"2025-11-13","cited_by_count":0,"area":"lr"},{"id":"2601.14599","title":"Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective","created":"2026-01-21","cited_by_count":0,"area":"lr"},{"id":"2602.00998","title":"Reliable Use of Lemmas via Eligibility Reasoning and Section$-$Aware Reinforcement Learning","created":"2026-02-01","cited_by_count":0,"area":"lr"},{"id":"2603.06416","title":"Evaluation of Deontic Conditional Reasoning in Large Language Models: The Case of Wason's Selection Task","created":"2026-03-06","cited_by_count":0,"area":"lr"},{"id":"2604.03374","title":"CresOWLve: Benchmarking Creative Problem-Solving Over Real-World Knowledge","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2607.05992","title":"PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2609.07103","title":"Revisiting Complete Reasoning Traces for Post-Training","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.33220","title":"When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.02015","title":"On Language Drift during RLVR Post-Training","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.15778","title":"Who Sets the Pace of Judge Hacking? Judge Capability versus the Policy-Judge Gap","created":"2026-10-11","cited_by_count":0,"area":"lr"},{"id":"2610.18598","title":"Rethinking Projector Training in Multimodal LLMs","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}