{"total":34,"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":"2604.10688","title":"SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting","created":"2026-04-12","cited_by_count":43,"area":"lr"},{"id":"2605.06130","title":"Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2604.09459","title":"From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models","created":"2026-04-10","cited_by_count":23,"area":"lr"},{"id":"2512.20745","title":"AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent","created":"2025-12-23","cited_by_count":17,"area":"lr"},{"id":"2510.15414","title":"MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs","created":"2025-10-17","cited_by_count":16,"area":"lr"},{"id":"2605.11853","title":"GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation","created":"2026-05-12","cited_by_count":12,"area":"lr"},{"id":"2511.02303","title":"Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation","created":"2025-11-04","cited_by_count":11,"area":"lr"},{"id":"2510.25510","title":"MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL","created":"2025-10-29","cited_by_count":10,"area":"lr"},{"id":"2512.00908","title":"Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs","created":"2025-11-30","cited_by_count":10,"area":"lr"},{"id":"2604.14267","title":"Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization","created":"2026-04-15","cited_by_count":9,"area":"lr"},{"id":"2511.11113","title":"VIDEOP2R: Video Understanding from Perception to Reasoning","created":"2025-11-14","cited_by_count":8,"area":"lr"},{"id":"2604.01840","title":"Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models","created":"2026-04-02","cited_by_count":7,"area":"lr"},{"id":"2606.09348","title":"PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment","created":"2026-06-08","cited_by_count":6,"area":"lr"},{"id":"2510.15990","title":"Can GRPO Help LLMs Transcend Their Pretraining Origin?","created":"2025-10-14","cited_by_count":5,"area":"lr"},{"id":"2601.22776","title":"TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2602.22193","title":"Improving Parametric Knowledge Access in Reasoning Language Models","created":"2026-02-25","cited_by_count":5,"area":"lr"},{"id":"2607.13501","title":"LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning","created":"2026-07-15","cited_by_count":5,"area":"lr"},{"id":"2510.26020","title":"PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoning","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2605.04984","title":"Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2604.13491","title":"FiRe: Fine-grained Multimodal Reasoning for Enhanced Image Generation","created":"2026-04-15","cited_by_count":3,"area":"lr"},{"id":"2604.17912","title":"Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-Thought","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2607.25816","title":"Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL","created":"2026-07-28","cited_by_count":2,"area":"lr"},{"id":"2601.16480","title":"TL-GRPO: Turn-Level RL for Reasoning-Guided Iterative Optimization","created":"2026-01-23","cited_by_count":1,"area":"lr"},{"id":"2604.18235","title":"Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents","created":"2026-04-20","cited_by_count":1,"area":"lr"},{"id":"2609.29050","title":"SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL","created":"2026-09-24","cited_by_count":1,"area":"lr"},{"id":"2602.23440","title":"Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2605.18799","title":"ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2606.08875","title":"Can the Environment Speak for Itself? $T^{2}$-GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents","created":"2026-06-07","cited_by_count":0,"area":"lr"},{"id":"2607.27652","title":"Harness-G: A Graph-Structured Harness for Search Agents","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2608.05139","title":"Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2609.16268","title":"Spurious Tool Use: When RL Agents Learn the Wrong Reason to Act","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.25463","title":"Rollout Efficiency in Reinforcement Learning for Reasoning Large Language Models: A Taxonomy and Future Directions","created":"2026-09-21","cited_by_count":0,"area":"lr"},{"id":"2609.35472","title":"Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}