{"total":36,"rows":[{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210,"area":"lr"},{"id":"2505.05410","title":"Reasoning Models Don't Always Say What They Think","created":"2025-05-08","cited_by_count":415,"area":"lr"},{"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":"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":"2501.09732","title":"Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps","created":"2025-01-16","cited_by_count":234,"area":"lr"},{"id":"2502.10325","title":"Process Reward Models for LLM Agents: Practical Framework and Directions","created":"2025-02-14","cited_by_count":85,"area":"lr"},{"id":"2509.15207","title":"FlowRL: Matching Reward Distributions for LLM Reasoning","created":"2025-09-18","cited_by_count":40,"area":"lr"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2501.17974","title":"Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization","created":"2025-01-29","cited_by_count":29,"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":"2509.26209","title":"Diversity-Incentivized Exploration for Versatile Reasoning","created":"2025-09-30","cited_by_count":28,"area":"lr"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"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":"2509.22047","title":"MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems","created":"2025-09-26","cited_by_count":23,"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":"2504.04524","title":"Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning","created":"2025-04-06","cited_by_count":12,"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":"2602.19895","title":"DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning","created":"2026-02-23","cited_by_count":9,"area":"lr"},{"id":"2402.03469","title":"Rethinking the Role of Proxy Rewards in Language Model Alignment","created":"2024-02-02","cited_by_count":7,"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":"2603.04948","title":"$\\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space","created":"2026-03-05","cited_by_count":5,"area":"lr"},{"id":"2505.14264","title":"AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin","created":"2025-05-20","cited_by_count":3,"area":"lr"},{"id":"2604.02341","title":"LLM Reasoning with Process Rewards for Outcome-Guided Steps","created":"2026-02-08","cited_by_count":3,"area":"lr"},{"id":"2604.04648","title":"From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism","created":"2026-04-06","cited_by_count":3,"area":"lr"},{"id":"2502.13207","title":"Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation","created":"2025-02-18","cited_by_count":1,"area":"lr"},{"id":"2511.22242","title":"Rethinking Test Time Scaling for Flow-Matching Generative Models","created":"2025-11-27","cited_by_count":1,"area":"lr"},{"id":"2603.10009","title":"Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment","created":"2026-02-17","cited_by_count":1,"area":"lr"},{"id":"2606.05263","title":"Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2606.30627","title":"Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models","created":"2026-06-29","cited_by_count":1,"area":"lr"},{"id":"2605.26037","title":"Peak-Then-Collapse and the Four Interface Channels of Knowledge-Graph Tool Use","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2605.29009","title":"Label-Free Reinforcement Learning via Cross-Model Entropy","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.05932","title":"A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR","created":"2026-06-04","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":"2610.05170","title":"Verification Trap: Understanding Test-Time Selection Failures under False Premises in Code Generation","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.06439","title":"Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models","created":"2026-10-05","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}