{"total":69,"rows":[{"id":"2504.20571","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","created":"2025-04-29","cited_by_count":295,"area":"lr"},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281,"area":"lr"},{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209,"area":"lr"},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2506.02177","title":"Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts","created":"2025-06-02","cited_by_count":113,"area":"lr"},{"id":"2505.17813","title":"Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning","created":"2025-05-23","cited_by_count":85,"area":"lr"},{"id":"2504.21370","title":"ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning","created":"2025-04-30","cited_by_count":72,"area":"lr"},{"id":"2505.10832","title":"Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL","created":"2025-05-16","cited_by_count":62,"area":"lr"},{"id":"2509.13769","title":"AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving","created":"2025-09-17","cited_by_count":58,"area":"lr"},{"id":"2505.24133","title":"R-KV: Redundancy-aware KV Cache Compression for Reasoning Models","created":"2025-05-30","cited_by_count":54,"area":"lr"},{"id":"2507.04632","title":"Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?","created":"2025-07-07","cited_by_count":52,"area":"lr"},{"id":"2507.21848","title":"EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity","created":"2025-07-29","cited_by_count":41,"area":"lr"},{"id":"2504.09762","title":"Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!","created":"2025-04-14","cited_by_count":37,"area":"lr"},{"id":"2504.13941","title":"Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning","created":"2025-04-15","cited_by_count":31,"area":"lr"},{"id":"2507.02076","title":"Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2506.09016","title":"SPEED-RL: Faster Training of Reasoning Models via Online Curriculum Learning","created":"2025-06-10","cited_by_count":29,"area":"lr"},{"id":"2505.19640","title":"Interleaved Reasoning for Large Language Models via Reinforcement Learning","created":"2025-05-26","cited_by_count":21,"area":"lr"},{"id":"2505.11225","title":"HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2510.06672","title":"XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation","created":"2025-10-08","cited_by_count":18,"area":"lr"},{"id":"2505.11827","title":"Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning","created":"2025-05-17","cited_by_count":16,"area":"lr"},{"id":"2505.21178","title":"Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning","created":"2025-05-27","cited_by_count":16,"area":"lr"},{"id":"2510.26418","title":"Chain-of-Thought Hijacking","created":"2025-10-30","cited_by_count":16,"area":"lr"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2510.02172","title":"RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization","created":"2025-10-02","cited_by_count":15,"area":"lr"},{"id":"2505.14216","title":"Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning","created":"2025-05-20","cited_by_count":14,"area":"lr"},{"id":"2505.17250","title":"ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models","created":"2025-05-22","cited_by_count":14,"area":"lr"},{"id":"2507.06892","title":"Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2508.09670","title":"MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement","created":"2025-08-13","cited_by_count":14,"area":"lr"},{"id":"2602.01970","title":"Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models","created":"2026-02-02","cited_by_count":14,"area":"lr"},{"id":"2505.08392","title":"Adaptive GoGI-Skip: Coupling Goal-Gradient Importance with Dynamic Uncertainty for Efficient Reasoning","created":"2025-05-13","cited_by_count":12,"area":"lr"},{"id":"2507.08297","title":"KAT-V1: Kwai-AutoThink Technical Report","created":"2025-07-11","cited_by_count":12,"area":"lr"},{"id":"2603.10887","title":"Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models","created":"2026-03-11","cited_by_count":11,"area":"lr"},{"id":"2505.21097","title":"Thinker: Learning to Think Fast and Slow","created":"2025-05-27","cited_by_count":10,"area":"lr"},{"id":"2507.06573","title":"From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization","created":"2025-07-09","cited_by_count":10,"area":"lr"},{"id":"2512.24574","title":"Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time","created":"2025-12-31","cited_by_count":10,"area":"lr"},{"id":"2603.25184","title":"Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model","created":"2026-03-26","cited_by_count":10,"area":"lr"},{"id":"2510.01459","title":"LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning","created":"2025-10-01","cited_by_count":9,"area":"lr"},{"id":"2509.23629","title":"Emergent Slow Thinking in LLMs as Inverse Tree Freezing","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2601.11340","title":"Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2604.11056","title":"Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR","created":"2026-04-13","cited_by_count":8,"area":"lr"},{"id":"2505.13697","title":"RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMs","created":"2025-05-19","cited_by_count":7,"area":"lr"},{"id":"2507.17307","title":"R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning","created":"2025-07-23","cited_by_count":7,"area":"lr"},{"id":"2505.14403","title":"Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning","created":"2025-05-20","cited_by_count":6,"area":"lr"},{"id":"2505.20296","title":"Reasoning LLMs are Wandering Solution Explorers","created":"2025-05-26","cited_by_count":6,"area":"lr"},{"id":"2506.08672","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","created":"2025-06-10","cited_by_count":6,"area":"lr"},{"id":"2510.12838","title":"A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning","created":"2025-10-13","cited_by_count":6,"area":"lr"},{"id":"2512.12008","title":"Hold Onto That Thought: Assessing KV Cache Compression On Reasoning","created":"2025-12-12","cited_by_count":6,"area":"lr"},{"id":"2603.14251","title":"Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2605.03314","title":"When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning","created":"2026-05-05","cited_by_count":5,"area":"lr"},{"id":"2505.13718","title":"Warm Up Before You Train: Unlocking General Reasoning in Resource-Constrained Settings","created":"2025-05-19","cited_by_count":4,"area":"lr"},{"id":"2510.03805","title":"Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models","created":"2025-10-04","cited_by_count":4,"area":"lr"},{"id":"2510.04072","title":"Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2510.24794","title":"MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models","created":"2025-10-27","cited_by_count":4,"area":"lr"},{"id":"2604.05164","title":"Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2509.25958","title":"RoRecomp: Enhancing Reasoning Efficiency via Rollout Response Recomposition in Reinforcement Learning","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2510.10168","title":"Concise Reasoning in the Lens of Lagrangian Optimization","created":"2025-10-11","cited_by_count":3,"area":"lr"},{"id":"2510.23486","title":"Learning to Reason Efficiently with Discounted Reinforcement Learning","created":"2025-10-27","cited_by_count":3,"area":"lr"},{"id":"2602.10004","title":"ESTAR: Early-Stopping Token-Aware Reasoning For Efficient Inference","created":"2026-02-10","cited_by_count":3,"area":"lr"},{"id":"2603.00578","title":"Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs","created":"2026-02-28","cited_by_count":3,"area":"lr"},{"id":"2606.11164","title":"ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2606.22716","title":"Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards","created":"2026-06-21","cited_by_count":3,"area":"lr"},{"id":"2511.02690","title":"Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2602.14917","title":"BFS-PO: Best-First Search for Large Reasoning Models","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2607.27610","title":"Kalman Meets Curriculum: Efficient Dynamic Prompt Selection for Adaptive RL Finetuning","created":"2026-07-30","cited_by_count":2,"area":"lr"},{"id":"2510.00546","title":"ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding","created":"2025-10-01","cited_by_count":1,"area":"lr"},{"id":"2602.01198","title":"A State-Transition Framework for Efficient LLM Reasoning","created":"2026-02-01","cited_by_count":1,"area":"lr"},{"id":"2606.17803","title":"Continual Self-Improvement with Lightweight Experiential Latent Memories","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2509.19762","title":"The Conductor and the Engine: A Path Towards Co-Designed Reasoning","created":"2025-09-24","cited_by_count":0,"area":"lr"},{"id":"2610.19890","title":"Frustratingly Easy Majority Voting Using Length Conditioning","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}