{"total":70,"rows":[{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104,"area":"lr"},{"id":"2507.08838","title":"wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models","created":"2025-07-07","cited_by_count":71,"area":"lr"},{"id":"2506.05316","title":"Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay","created":"2025-06-05","cited_by_count":56,"area":"lr"},{"id":"2510.00915","title":"Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers","created":"2025-10-01","cited_by_count":45,"area":"lr"},{"id":"2509.19803","title":"VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models","created":"2025-09-24","cited_by_count":36,"area":"lr"},{"id":"2505.11277","title":"Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning","created":"2025-05-16","cited_by_count":35,"area":"lr"},{"id":"2505.22257","title":"Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training","created":"2025-05-28","cited_by_count":34,"area":"lr"},{"id":"2509.18521","title":"APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation","created":"2025-09-23","cited_by_count":30,"area":"lr"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2507.17842","title":"Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning","created":"2025-07-23","cited_by_count":19,"area":"lr"},{"id":"2505.11849","title":"VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation","created":"2025-05-17","cited_by_count":16,"area":"lr"},{"id":"2505.12366","title":"DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization","created":"2025-05-18","cited_by_count":16,"area":"lr"},{"id":"2507.06167","title":"Skywork-R1V3 Technical Report","created":"2025-07-08","cited_by_count":16,"area":"lr"},{"id":"2506.22200","title":"EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework","created":"2025-06-27","cited_by_count":14,"area":"lr"},{"id":"2507.08182","title":"CTRLS: Chain-of-Thought Reasoning via Latent State-Transition","created":"2025-07-10","cited_by_count":14,"area":"lr"},{"id":"2509.03059","title":"Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers","created":"2025-09-03","cited_by_count":14,"area":"lr"},{"id":"2510.18924","title":"Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients","created":"2025-10-21","cited_by_count":13,"area":"lr"},{"id":"2601.02346","title":"Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling","created":"2026-01-05","cited_by_count":13,"area":"lr"},{"id":"2508.12281","title":"Legal$\\Delta$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain","created":"2025-08-17","cited_by_count":12,"area":"lr"},{"id":"2602.17025","title":"WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning","created":"2026-02-19","cited_by_count":12,"area":"lr"},{"id":"2604.00698","title":"Learning to Hint for Reinforcement Learning","created":"2026-04-01","cited_by_count":12,"area":"lr"},{"id":"2509.22611","title":"Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning","created":"2025-09-26","cited_by_count":11,"area":"lr"},{"id":"2510.23049","title":"Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients","created":"2025-10-27","cited_by_count":11,"area":"lr"},{"id":"2511.18902","title":"VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL","created":"2025-11-24","cited_by_count":11,"area":"lr"},{"id":"2603.13134","title":"When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO","created":"2026-03-13","cited_by_count":10,"area":"lr"},{"id":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","cited_by_count":9,"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":"2602.21189","title":"Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training","created":"2026-02-24","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":"2605.21125","title":"Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation","created":"2026-05-20","cited_by_count":7,"area":"lr"},{"id":"2507.00951","title":"Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact","created":"2025-07-01","cited_by_count":6,"area":"lr"},{"id":"2508.07382","title":"Pentest-R1: Towards Autonomous Penetration Testing Reasoning Optimized via Two-Stage Reinforcement Learning","created":"2025-08-10","cited_by_count":5,"area":"lr"},{"id":"2607.21273","title":"The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and The Channel, Not the Content, Decides What Works","created":"2026-07-23","cited_by_count":5,"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":"2512.19554","title":"CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning","created":"2025-12-22","cited_by_count":4,"area":"lr"},{"id":"2601.22448","title":"HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning","created":"2026-01-30","cited_by_count":4,"area":"lr"},{"id":"2602.11128","title":"Asymmetric Prompt Weighting for Reinforcement Learning with Verifiable Rewards","created":"2026-02-11","cited_by_count":4,"area":"lr"},{"id":"2606.18844","title":"Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation","created":"2026-06-17","cited_by_count":4,"area":"lr"},{"id":"2604.14646","title":"Targeted Exploration via Unified Entropy Control for Reinforcement Learning","created":"2026-04-16","cited_by_count":3,"area":"lr"},{"id":"2605.06139","title":"Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex","created":"2026-05-07","cited_by_count":3,"area":"lr"},{"id":"2509.20616","title":"Training Task Reasoning LLM Agents for Multi-turn Task Planning via Single-turn Reinforcement Learning","created":"2025-09-24","cited_by_count":2,"area":"lr"},{"id":"2510.07790","title":"GCPO: When Contrast Fails, Go Gold","created":"2025-10-09","cited_by_count":2,"area":"lr"},{"id":"2603.27375","title":"Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models","created":"2026-03-28","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":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2509.21028","title":"SciTrek: Evaluating and Improving Long-Context Numerical Reasoning over Scientific Articles","created":"2025-09-25","cited_by_count":1,"area":"lr"},{"id":"2510.14828","title":"RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2601.22478","title":"Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models","created":"2026-01-30","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":"2604.20755","title":"V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimization","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2605.02263","title":"Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2607.12856","title":"Verifier-Based Reinforcement Fine-Tuning of Reasoning Models for Thermal Energy Storage Control","created":"2026-07-14","cited_by_count":1,"area":"lr"},{"id":"2609.02817","title":"Cliff: Learning Process Rewards from the First Mistake","created":"2026-09-02","cited_by_count":1,"area":"lr"},{"id":"2503.16304","title":"Bridging Technology and Humanities: Evaluating the Impact of Large Language Models on Social Sciences Research with DeepSeek-R1","created":"2025-03-20","cited_by_count":0,"area":"lr"},{"id":"2605.06755","title":"Gradient Extrapolation-Based Policy Optimization","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.07276","title":"Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.11726","title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.24331","title":"CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2606.28707","title":"BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards","created":"2026-06-27","cited_by_count":0,"area":"lr"},{"id":"2607.02983","title":"Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Models","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2607.18470","title":"RRPO: Reference-Relative Policy Optimization with Stratified Conditional Rollouts","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2607.27914","title":"Exact Action Values Are Not Enough: Rollout-Verified Reinforcement Fine-Tuning of a Reasoning Model for Multi-Zone VAV Control","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2608.27046","title":"Performance Foundations of Parallel & Distributed Reasoning Language Models","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2609.04063","title":"Spurious Advantage Hidden in GRPO","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.28385","title":"When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit Assignment","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.38018","title":"Prompts Live on an Arc: Gaussian Curricula in Fisher--Rao Coordinates for Rollout-Efficient GRPO","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.04158","title":"How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.04596","title":"DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation","created":"2026-10-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}