{"total":44,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2504.12216","title":"d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning","created":"2025-04-16","cited_by_count":186,"area":"lr"},{"id":"2503.23829","title":"Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains","created":"2025-03-31","cited_by_count":156,"area":"lr"},{"id":"2501.04682","title":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought","created":"2025-01-08","cited_by_count":109,"area":"lr"},{"id":"2502.01718","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","created":"2025-02-03","cited_by_count":93,"area":"lr"},{"id":"2505.21493","title":"Reinforcing General Reasoning without Verifiers","created":"2025-05-27","cited_by_count":77,"area":"lr"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2602.22817","title":"Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-02-26","cited_by_count":49,"area":"lr"},{"id":"2504.04736","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","created":"2025-04-07","cited_by_count":45,"area":"lr"},{"id":"2503.18929","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","created":"2025-03-24","cited_by_count":29,"area":"lr"},{"id":"2506.13923","title":"Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models","created":"2025-06-16","cited_by_count":18,"area":"lr"},{"id":"2503.04378","title":"HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks","created":"2025-03-06","cited_by_count":17,"area":"lr"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2504.15077","title":"Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL","created":"2025-04-21","cited_by_count":14,"area":"lr"},{"id":"2506.11027","title":"From Reasoning to Code: GRPO Optimization for Underrepresented Languages","created":"2025-05-20","cited_by_count":11,"area":"lr"},{"id":"2511.01633","title":"Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving","created":"2025-11-03","cited_by_count":10,"area":"lr"},{"id":"2506.02211","title":"Improving LLM-Generated Code Quality with GRPO","created":"2025-06-02","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":"2509.22824","title":"Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning","created":"2025-09-26","cited_by_count":7,"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":"2604.06079","title":"Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning","created":"2026-04-07","cited_by_count":6,"area":"lr"},{"id":"2604.03144","title":"InCoder-32B-Thinking: Industrial Code World Model for Thinking","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2601.09085","title":"MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2507.05065","title":"Replacing thinking with tool usage enables reasoning in small language models","created":"2025-07-07","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":"2602.19069","title":"Asking the Right Questions: Improving Reasoning with Generated Stepping Stones","created":"2026-02-22","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":"2608.00181","title":"Cross-Benchmark Generalization in Long-Horizon Agents","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2506.21560","title":"Reinforcement learning fine-tuning of language model for instruction following and math reasoning","created":"2025-06-11","cited_by_count":0,"area":"lr"},{"id":"2508.02091","title":"CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search","created":"2025-08-04","cited_by_count":0,"area":"lr"},{"id":"2509.24207","title":"Humanline: Online Alignment as Perceptual Loss","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2509.25455","title":"PIPer: On-Device Environment Setup via Online Reinforcement Learning","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2510.21830","title":"GAPO: Robust Advantage Estimation for Real-World Code LLMs","created":"2025-10-22","cited_by_count":0,"area":"lr"},{"id":"2604.20926","title":"Learning Reasoning World Models for Parallel Code","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2605.11299","title":"Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.14539","title":"Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.21235","title":"LamPO: A Lambda Style Policy Optimization for Reasoning Language Models","created":"2026-05-20","cited_by_count":0,"area":"lr"},{"id":"2606.29354","title":"When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning","created":"2026-06-28","cited_by_count":0,"area":"lr"},{"id":"2607.01490","title":"Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2607.20908","title":"Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation","created":"2026-07-23","cited_by_count":0,"area":"lr"},{"id":"2609.27572","title":"DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.39021","title":"Frame Differential On-Policy Self-Distillation for Video Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.04737","title":"PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution","created":"2026-10-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}