{"total":118,"rows":[{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304,"area":"lr"},{"id":"2604.13016","title":"Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe","created":"2026-04-14","cited_by_count":299,"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":"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":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172,"area":"lr"},{"id":"2508.10751","title":"Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models","created":"2025-08-14","cited_by_count":138,"area":"lr"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2508.13167","title":"Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL","created":"2025-08-06","cited_by_count":80,"area":"lr"},{"id":"2506.13284","title":"AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy","created":"2025-06-16","cited_by_count":77,"area":"lr"},{"id":"2508.08221","title":"Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning","created":"2025-08-11","cited_by_count":56,"area":"lr"},{"id":"2510.10150","title":"Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective","created":"2025-10-11","cited_by_count":52,"area":"lr"},{"id":"2604.10688","title":"SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting","created":"2026-04-12","cited_by_count":43,"area":"lr"},{"id":"2507.15778","title":"Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR","created":"2025-07-21","cited_by_count":39,"area":"lr"},{"id":"2508.07629","title":"Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization","created":"2025-08-11","cited_by_count":39,"area":"lr"},{"id":"2508.03440","title":"LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking","created":"2025-08-05","cited_by_count":38,"area":"lr"},{"id":"2510.08049","title":"A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models","created":"2025-10-09","cited_by_count":38,"area":"lr"},{"id":"2510.11701","title":"Demystifying Reinforcement Learning in Agentic Reasoning","created":"2025-10-13","cited_by_count":33,"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":"2509.13232","title":"Single-stream Policy Optimization","created":"2025-09-16","cited_by_count":28,"area":"lr"},{"id":"2603.19835","title":"FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization","created":"2026-03-20","cited_by_count":25,"area":"lr"},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2508.02260","title":"Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning","created":"2025-08-04","cited_by_count":21,"area":"lr"},{"id":"2508.15827","title":"Mini-Omni-Reasoner: Token-Level Thinking-in-Speaking in Large Speech Models","created":"2025-08-18","cited_by_count":21,"area":"lr"},{"id":"2511.05993","title":"Revisiting Entropy in Reinforcement Learning for Large Reasoning Models","created":"2025-11-08","cited_by_count":21,"area":"lr"},{"id":"2507.18391","title":"Revisiting LLM Reasoning via Information Bottleneck","created":"2025-07-24","cited_by_count":19,"area":"lr"},{"id":"2510.10409","title":"Trace Length is a Simple Uncertainty Signal in Reasoning Models","created":"2025-10-12","cited_by_count":19,"area":"lr"},{"id":"2512.20745","title":"AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent","created":"2025-12-23","cited_by_count":17,"area":"lr"},{"id":"2512.21514","title":"DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO","created":"2025-12-25","cited_by_count":17,"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":"2509.26628","title":"Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models","created":"2025-09-30","cited_by_count":13,"area":"lr"},{"id":"2605.13230","title":"Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence","created":"2026-05-13","cited_by_count":13,"area":"lr"},{"id":"2507.19766","title":"UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities","created":"2025-07-26","cited_by_count":11,"area":"lr"},{"id":"2508.09883","title":"Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning","created":"2025-08-13","cited_by_count":11,"area":"lr"},{"id":"2509.25454","title":"DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2510.06036","title":"Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?","created":"2025-10-07","cited_by_count":11,"area":"lr"},{"id":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2602.17550","title":"MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2506.14731","title":"Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs","created":"2025-06-17","cited_by_count":10,"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":"2507.12885","title":"VAR-MATH: Probing True Mathematical Reasoning in LLMS via Symbolic Multi-Instance Benchmarks","created":"2025-07-17","cited_by_count":8,"area":"lr"},{"id":"2602.20722","title":"Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning","created":"2026-02-24","cited_by_count":8,"area":"lr"},{"id":"2510.22543","title":"FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning","created":"2025-10-26","cited_by_count":7,"area":"lr"},{"id":"2509.21070","title":"ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning","created":"2025-09-25","cited_by_count":6,"area":"lr"},{"id":"2509.24375","title":"Reinforcement Mid-Training","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2512.18196","title":"LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision","created":"2025-12-20","cited_by_count":6,"area":"lr"},{"id":"2602.13935","title":"Statistical Early Stopping for Reasoning Models","created":"2026-02-15","cited_by_count":6,"area":"lr"},{"id":"2506.18330","title":"Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning","created":"2025-06-23","cited_by_count":5,"area":"lr"},{"id":"2509.26226","title":"Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners","created":"2025-09-30","cited_by_count":5,"area":"lr"},{"id":"2510.25528","title":"Zero Reinforcement Learning Towards General Domains","created":"2025-10-29","cited_by_count":5,"area":"lr"},{"id":"2602.01204","title":"ASTER: Agentic Scaling with Tool-integrated Extended Reasoning","created":"2026-02-01","cited_by_count":5,"area":"lr"},{"id":"2602.01365","title":"When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning","created":"2026-02-01","cited_by_count":5,"area":"lr"},{"id":"2604.01591","title":"ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement","created":"2026-04-02","cited_by_count":5,"area":"lr"},{"id":"2608.11829","title":"Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling","created":"2026-08-12","cited_by_count":5,"area":"lr"},{"id":"2507.21645","title":"Libra: Assessing and Improving Reward Model by Learning to Think","created":"2025-07-29","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":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2511.11373","title":"MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pipeline Parallelism","created":"2025-11-14","cited_by_count":4,"area":"lr"},{"id":"2601.01562","title":"Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement","created":"2026-01-04","cited_by_count":4,"area":"lr"},{"id":"2602.03978","title":"Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2506.04734","title":"Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design","created":"2025-06-05","cited_by_count":3,"area":"lr"},{"id":"2509.15148","title":"ATTS: Asynchronous Test-Time Scaling via Conformal Prediction","created":"2025-09-18","cited_by_count":3,"area":"lr"},{"id":"2510.17498","title":"Deep Self-Evolving Reasoning","created":"2025-10-20","cited_by_count":3,"area":"lr"},{"id":"2510.25101","title":"KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA","created":"2025-10-29","cited_by_count":3,"area":"lr"},{"id":"2510.26109","title":"Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2510.26519","title":"Think Outside the Policy: In-Context Steered Policy Optimization","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2601.22249","title":"FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2602.06319","title":"Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2603.06032","title":"StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision","created":"2026-03-06","cited_by_count":3,"area":"lr"},{"id":"2603.18886","title":"Reasoning over mathematical objects: on-policy reward modeling and test time aggregation","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2603.22687","title":"GeoTikzBridge: Advancing Multimodal Code Generation for Geometric Perception and Reasoning","created":"2026-03-24","cited_by_count":3,"area":"lr"},{"id":"2606.19236","title":"STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2510.07958","title":"A$^2$Search: Ambiguity-Aware Question Answering with Reinforcement Learning","created":"2025-10-09","cited_by_count":2,"area":"lr"},{"id":"2512.11470","title":"Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning","created":"2025-12-12","cited_by_count":2,"area":"lr"},{"id":"2601.20649","title":"P2S: Probabilistic Process Supervision for General-Domain Reasoning Question Answering","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"id":"2602.11639","title":"PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2603.13348","title":"AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints","created":"2026-03-07","cited_by_count":2,"area":"lr"},{"id":"2603.17368","title":"Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2604.18574","title":"When Can LLMs Learn to Reason with Weak Supervision?","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2606.00437","title":"EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing","created":"2026-05-30","cited_by_count":2,"area":"lr"},{"id":"2606.08543","title":"PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR","created":"2026-06-07","cited_by_count":2,"area":"lr"},{"id":"2608.26070","title":"Prefix Sliding for efficient test-time scaling","created":"2026-08-26","cited_by_count":2,"area":"lr"},{"id":"2508.05496","title":"InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2509.19681","title":"Calibrated Reasoning: An Explanatory Verifier for Dynamic and Efficient Problem-Solving","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2509.22044","title":"A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"id":"2510.07774","title":"Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards","created":"2025-10-09","cited_by_count":1,"area":"lr"},{"id":"2601.14716","title":"PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning","created":"2026-01-21","cited_by_count":1,"area":"lr"},{"id":"2601.21476","title":"Thinking Seeds: Leveraging Historical Diversity for Position-Aware RL in LLMs","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2601.23027","title":"Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2603.29957","title":"Think Anywhere in Code Generation","created":"2026-03-31","cited_by_count":1,"area":"lr"},{"id":"2604.04894","title":"Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2604.17957","title":"Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2605.00754","title":"Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring","created":"2026-05-01","cited_by_count":1,"area":"lr"},{"id":"2605.04960","title":"EP-GRPO: Entropy-Progress Aligned Group Relative Policy Optimization with Implicit Process Guidance","created":"2026-05-06","cited_by_count":1,"area":"lr"},{"id":"2605.07237","title":"Teaching Language Models to Think in Code","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.10158","title":"Unsupervised Process Reward Models","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2605.10344","title":"TMAS: Scaling Test-Time Compute via Multi-Agent Synergy","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2606.27378","title":"Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2607.16205","title":"It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches","created":"2026-05-07","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}