{"total":19,"rows":[{"id":"2506.19767","title":"SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning","created":"2025-06-24","cited_by_count":84,"area":"lr"},{"id":"2508.00222","title":"RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization","created":"2025-07-31","cited_by_count":35,"area":"lr"},{"id":"2507.14958","title":"MUR: Momentum Uncertainty guided Reasoning for Large Language Models","created":"2025-07-20","cited_by_count":17,"area":"lr"},{"id":"2510.04028","title":"The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View","created":"2025-10-05","cited_by_count":13,"area":"lr"},{"id":"2512.13095","title":"ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2601.03872","title":"Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning","created":"2026-01-07","cited_by_count":11,"area":"lr"},{"id":"2604.23747","title":"SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning","created":"2026-04-26","cited_by_count":9,"area":"lr"},{"id":"2604.12627","title":"KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance","created":"2026-04-14","cited_by_count":8,"area":"lr"},{"id":"2508.06944","title":"AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance","created":"2025-08-09","cited_by_count":5,"area":"lr"},{"id":"2505.24850","title":"Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning","created":"2025-05-30","cited_by_count":3,"area":"lr"},{"id":"2510.02227","title":"More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration","created":"2025-10-02","cited_by_count":3,"area":"lr"},{"id":"2511.09222","title":"Toward Honest Language Models for Deductive Reasoning","created":"2025-11-12","cited_by_count":3,"area":"lr"},{"id":"2606.18216","title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","created":"2026-06-16","cited_by_count":3,"area":"lr"},{"id":"2510.12643","title":"Reasoning Pattern Matters: Learning to Reason without Human Rationales","created":"2025-10-14","cited_by_count":2,"area":"lr"},{"id":"2605.22074","title":"From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning","created":"2026-05-21","cited_by_count":2,"area":"lr"},{"id":"2602.20197","title":"Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning","created":"2026-02-22","cited_by_count":1,"area":"lr"},{"id":"2605.18500","title":"Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2512.02580","title":"From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks","created":"2025-12-02","cited_by_count":0,"area":"lr"},{"id":"2610.19796","title":"Learning Perception to Action Rules through Reinforcement Learning for Theory-of-Mind Reasoning","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}