{"total":91,"rows":[{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485,"area":"lr"},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344,"area":"lr"},{"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":"2506.14245","title":"Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs","created":"2025-06-17","cited_by_count":289,"area":"lr"},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"id":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275,"area":"lr"},{"id":"2508.05004","title":"R-Zero: Self-Evolving Reasoning LLM from Zero Data","created":"2025-08-07","cited_by_count":228,"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":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"area":"lr"},{"id":"2508.05629","title":"On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification","created":"2025-08-07","cited_by_count":127,"area":"lr"},{"id":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111,"area":"lr"},{"id":"2505.12346","title":"SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization","created":"2025-05-18","cited_by_count":89,"area":"lr"},{"id":"2505.20347","title":"SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data","created":"2025-05-25","cited_by_count":51,"area":"lr"},{"id":"2509.21880","title":"No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping","created":"2025-09-26","cited_by_count":50,"area":"lr"},{"id":"2506.08745","title":"Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":46,"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":"2510.27606","title":"Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning","created":"2025-10-31","cited_by_count":41,"area":"lr"},{"id":"2506.17219","title":"No Free Lunch: Rethinking Internal Feedback for LLM Reasoning","created":"2025-06-20","cited_by_count":37,"area":"lr"},{"id":"2505.23590","title":"Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles","created":"2025-05-29","cited_by_count":36,"area":"lr"},{"id":"2505.22453","title":"First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training","created":"2025-05-28","cited_by_count":34,"area":"lr"},{"id":"2505.24718","title":"Reinforcing Video Reasoning with Focused Thinking","created":"2025-05-30","cited_by_count":31,"area":"lr"},{"id":"2511.19900","title":"Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning","created":"2025-11-25","cited_by_count":31,"area":"lr"},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2507.03112","title":"RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents","created":"2025-07-03","cited_by_count":25,"area":"lr"},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23,"area":"lr"},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2510.01833","title":"Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning","created":"2025-10-02","cited_by_count":19,"area":"lr"},{"id":"2608.06296","title":"On-Policy Self-Distillation without Any Supervision","created":"2026-08-06","cited_by_count":17,"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":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2509.00125","title":"Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning","created":"2025-08-29","cited_by_count":12,"area":"lr"},{"id":"2603.19880","title":"What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time","created":"2026-03-20","cited_by_count":12,"area":"lr"},{"id":"2505.19439","title":"Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers","created":"2025-05-26","cited_by_count":11,"area":"lr"},{"id":"2603.11682","title":"Entropy-Preserving Reinforcement Learning","created":"2026-03-12","cited_by_count":11,"area":"lr"},{"id":"2509.24981","title":"Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2602.12579","title":"VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction","created":"2026-02-13","cited_by_count":10,"area":"lr"},{"id":"2512.00499","title":"ESPO: Entropy Importance Sampling Policy Optimization","created":"2025-11-29","cited_by_count":9,"area":"lr"},{"id":"2602.19895","title":"DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning","created":"2026-02-23","cited_by_count":9,"area":"lr"},{"id":"2511.13612","title":"P1: Mastering Physics Olympiads with Reinforcement Learning","created":"2025-11-17","cited_by_count":8,"area":"lr"},{"id":"2512.13106","title":"TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning","created":"2025-12-15","cited_by_count":7,"area":"lr"},{"id":"2605.19444","title":"Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement Learning with Majority Voting","created":"2026-05-19","cited_by_count":7,"area":"lr"},{"id":"2508.12338","title":"Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective Feedback","created":"2025-08-17","cited_by_count":6,"area":"lr"},{"id":"2605.25864","title":"When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewards","created":"2026-05-25","cited_by_count":6,"area":"lr"},{"id":"2510.08026","title":"PEAR: Phase Entropy Aware Reward for Efficient Reasoning","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2604.08203","title":"MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning","created":"2026-04-09","cited_by_count":5,"area":"lr"},{"id":"2607.13643","title":"Consensus as Privileged Context for Label-Free Self-Distillation","created":"2026-07-15","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2509.25543","title":"Aligning Multilingual Reasoning with Verifiable Semantics from a High-Resource Expert Model","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2511.07124","title":"Think Consistently, Reason Efficiently: Energy-Based Calibration for Implicit Chain-of-Thought","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2601.04700","title":"PRISM: A Unified Framework for Post-Training LLMs Without Verifiable Rewards","created":"2026-01-08","cited_by_count":4,"area":"lr"},{"id":"2605.04984","title":"Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2606.01075","title":"On the Generalization Gap in Self-Evolving Language Model Reasoning","created":"2026-05-31","cited_by_count":4,"area":"lr"},{"id":"2606.08501","title":"Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models","created":"2026-06-07","cited_by_count":4,"area":"lr"},{"id":"2507.18122","title":"Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical Reasoning","created":"2025-07-24","cited_by_count":3,"area":"lr"},{"id":"2510.04116","title":"Searching Meta Reasoning Skeleton to Guide LLM Reasoning","created":"2025-10-05","cited_by_count":3,"area":"lr"},{"id":"2510.08977","title":"Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2511.16331","title":"Incorporating Self-Rewriting into Large Language Model Reasoning Reinforcement","created":"2025-11-20","cited_by_count":3,"area":"lr"},{"id":"2601.21804","title":"Distribution-Aware Reward Estimation for Test-Time Reinforcement Learning","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2602.00815","title":"Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement","created":"2026-01-31","cited_by_count":3,"area":"lr"},{"id":"2602.04620","title":"QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2603.18859","title":"RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2511.09865","title":"In-Token Rationality Optimization: Towards Accurate and Concise LLM Reasoning via Self-Feedback","created":"2025-11-13","cited_by_count":2,"area":"lr"},{"id":"2601.04973","title":"ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"id":"2601.14700","title":"DARL: Encouraging Diverse Answers for General Reasoning without Verifiers","created":"2026-01-21","cited_by_count":2,"area":"lr"},{"id":"2602.20132","title":"LAD: Learning Advantage Distribution for Reasoning","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2603.16223","title":"Dual Consensus: Escaping from Spurious Majority in Unsupervised RLVR via Two-Stage Vote Mechanism","created":"2026-03-17","cited_by_count":2,"area":"lr"},{"id":"2603.27977","title":"SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology","created":"2026-03-30","cited_by_count":2,"area":"lr"},{"id":"2604.03993","title":"Can LLMs Learn to Reason Robustly under Noisy Supervision?","created":"2026-04-05","cited_by_count":2,"area":"lr"},{"id":"2601.22521","title":"One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.16839","title":"Training Large Reasoning Models Efficiently via Progressive Thought Encoding","created":"2026-02-18","cited_by_count":1,"area":"lr"},{"id":"2603.04406","title":"CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2604.08468","title":"TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2604.11547","title":"Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach","created":"2026-04-13","cited_by_count":1,"area":"lr"},{"id":"2604.26326","title":"Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control","created":"2026-04-29","cited_by_count":1,"area":"lr"},{"id":"2605.11461","title":"Breaking $\\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2606.04503","title":"Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2606.04516","title":"GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2607.20553","title":"CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement Learning","created":"2026-07-15","cited_by_count":1,"area":"lr"},{"id":"2608.03545","title":"Hi-TTRL: Regulating Consensus with Hints for Test-Time Reinforcement Learning","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2510.13850","title":"Revisiting the UID Hypothesis in LLM Reasoning Traces","created":"2025-10-11","cited_by_count":0,"area":"lr"},{"id":"2602.02979","title":"CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning","created":"2026-02-03","cited_by_count":0,"area":"lr"},{"id":"2602.05494","title":"A Unified Framework for Rethinking Policy Divergence Measures in GRPO","created":"2026-02-05","cited_by_count":0,"area":"lr"},{"id":"2605.08186","title":"Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models","created":"2026-05-05","cited_by_count":0,"area":"lr"},{"id":"2605.22620","title":"Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2608.09324","title":"CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2609.30192","title":"SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2610.00903","title":"Sharpen Before You Adapt: Data-Free Entry-State Sharpening for Test-Time Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.02695","title":"Test-time Calibration Learning for Large Language Model Reasoning","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.18388","title":"ReDiS: Reasoning-Diagnosis Self-Evolution for Multimodal Reasoning in Remote Sensing","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}