{"total":35,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2505.11821","title":"Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit Assignment","created":"2025-05-17","cited_by_count":79,"area":"lr"},{"id":"2505.10832","title":"Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL","created":"2025-05-16","cited_by_count":62,"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":"2505.19866","title":"HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation","created":"2025-05-26","cited_by_count":18,"area":"lr"},{"id":"2509.26578","title":"Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning","created":"2025-09-30","cited_by_count":14,"area":"lr"},{"id":"2601.14209","title":"InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning","created":"2026-01-20","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":"2601.18984","title":"Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning","created":"2026-01-26","cited_by_count":11,"area":"lr"},{"id":"2506.04611","title":"Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning","created":"2025-06-05","cited_by_count":9,"area":"lr"},{"id":"2510.22255","title":"PACR: Progressively Ascending Confidence Reward for LLM Reasoning","created":"2025-10-25","cited_by_count":9,"area":"lr"},{"id":"2511.20718","title":"Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization","created":"2025-11-25","cited_by_count":9,"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":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2507.15698","title":"CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning","created":"2025-07-21","cited_by_count":5,"area":"lr"},{"id":"2605.05965","title":"Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVR","created":"2026-05-07","cited_by_count":5,"area":"lr"},{"id":"2508.06412","title":"Sample-efficient LLM Optimization with Reset Replay","created":"2025-08-08","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":"2603.16253","title":"Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2603.28135","title":"CoT2-Meta: Budgeted Metacognitive Control for Test-Time Reasoning","created":"2026-03-30","cited_by_count":4,"area":"lr"},{"id":"2604.10660","title":"Efficient Process Reward Modeling via Contrastive Mutual Information","created":"2026-04-12","cited_by_count":4,"area":"lr"},{"id":"2606.10646","title":"How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2601.08403","title":"Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs","created":"2026-01-13","cited_by_count":1,"area":"lr"},{"id":"2602.10224","title":"Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models","created":"2026-02-10","cited_by_count":1,"area":"lr"},{"id":"2604.23318","title":"Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance","created":"2026-04-25","cited_by_count":1,"area":"lr"},{"id":"2605.07353","title":"Confidence-Aware Alignment Makes Reasoning LLMs More Reliable","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":"2607.11506","title":"SCOPE-RL: Optimizing Reasoning Paths Before and After Success","created":"2026-07-13","cited_by_count":1,"area":"lr"},{"id":"2608.03119","title":"Don't Peek at the Answer: Outcome-Masked Group Relative Policy Optimization for Label-Free RLVR","created":"2026-08-04","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":"2605.07276","title":"Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2608.12585","title":"Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2609.39220","title":"Learning Process Rewards via Reasoning State Propagation","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39402","title":"Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.16593","title":"Double-Rollout Reinforcement Learning with Sampling-based Reward Estimation","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}