{"total":21,"rows":[{"id":"2504.07615","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","created":"2025-04-10","cited_by_count":526,"area":"lr"},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2505.24864","title":"ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models","created":"2025-05-30","cited_by_count":194,"area":"lr"},{"id":"2412.14135","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","created":"2024-12-18","cited_by_count":50,"area":"lr"},{"id":"2502.01839","title":"Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification","created":"2025-02-03","cited_by_count":50,"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":"2505.18807","title":"Mitigating Deceptive Alignment via Self-Monitoring","created":"2025-05-24","cited_by_count":29,"area":"lr"},{"id":"2505.13026","title":"Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs","created":"2025-05-19","cited_by_count":25,"area":"lr"},{"id":"2503.13551","title":"Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models","created":"2025-03-16","cited_by_count":18,"area":"lr"},{"id":"2504.05294","title":"Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations","created":"2025-04-07","cited_by_count":9,"area":"lr"},{"id":"2503.10573","title":"Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approach","created":"2025-03-13","cited_by_count":8,"area":"lr"},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2602.13953","title":"QuRL: Efficient Reinforcement Learning with Quantized Rollout","created":"2026-02-15","cited_by_count":8,"area":"lr"},{"id":"2504.20157","title":"Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models","created":"2025-04-28","cited_by_count":5,"area":"lr"},{"id":"2601.23086","title":"Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2507.20150","title":"The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models","created":"2025-07-27","cited_by_count":3,"area":"lr"},{"id":"2605.02269","title":"Towards Understanding Specification Gaming in Reasoning Models","created":"2026-05-04","cited_by_count":3,"area":"lr"},{"id":"2509.13081","title":"Shaping Explanations: Semantic Reward Modeling with Encoder-Only Transformers for GRPO","created":"2025-09-16","cited_by_count":2,"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":"2609.33220","title":"When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.15778","title":"Who Sets the Pace of Judge Hacking? Judge Capability versus the Policy-Judge Gap","created":"2026-10-11","cited_by_count":0,"area":"lr"}],"next_cursor":null}