{"total":29,"rows":[{"id":"2509.25140","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","created":"2025-09-29","cited_by_count":284,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2511.16043","title":"Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning","created":"2025-11-20","cited_by_count":75,"area":"lr"},{"id":"2510.10150","title":"Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective","created":"2025-10-11","cited_by_count":52,"area":"lr"},{"id":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34,"area":"lr"},{"id":"2510.11701","title":"Demystifying Reinforcement Learning in Agentic Reasoning","created":"2025-10-13","cited_by_count":33,"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":"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":"2603.22117","title":"On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation","created":"2026-03-23","cited_by_count":13,"area":"lr"},{"id":"2511.23031","title":"From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning","created":"2025-11-28","cited_by_count":9,"area":"lr"},{"id":"2601.03823","title":"Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning","created":"2026-01-07","cited_by_count":9,"area":"lr"},{"id":"2603.03825","title":"From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning","created":"2026-03-04","cited_by_count":8,"area":"lr"},{"id":"2605.14054","title":"Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning","created":"2026-05-13","cited_by_count":7,"area":"lr"},{"id":"2510.05132","title":"Training Large Language Models To Reason In Parallel With Global Forking Tokens","created":"2025-10-01","cited_by_count":6,"area":"lr"},{"id":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2512.07558","title":"ReLaX: Reasoning with Latent Exploration for Large Reasoning Models","created":"2025-12-08","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":"2606.05402","title":"ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces","created":"2026-06-03","cited_by_count":5,"area":"lr"},{"id":"2509.23946","title":"Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm","created":"2025-09-28","cited_by_count":2,"area":"lr"},{"id":"2510.08222","title":"Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens","created":"2025-10-09","cited_by_count":2,"area":"lr"},{"id":"2510.10813","title":"The Fragility of Strategic Thinking in Large Language Models","created":"2025-10-12","cited_by_count":2,"area":"lr"},{"id":"2602.14469","title":"Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2511.00710","title":"Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models","created":"2025-11-01","cited_by_count":1,"area":"lr"},{"id":"2603.22871","title":"Dynamical Systems Theory Behind a Hierarchical Reasoning Model","created":"2026-03-24","cited_by_count":1,"area":"lr"},{"id":"2604.00130","title":"Hierarchical Chain-of-Thought: Enhancing LLM Reasoning Performance and Efficiency","created":"2026-03-31","cited_by_count":1,"area":"lr"},{"id":"2604.04894","title":"Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2604.08690","title":"Skip-Connected Policy Optimization for Implicit Advantage","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2604.18936","title":"Fine-Tuning Small Reasoning Models for Quantum Field Theory","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2608.30632","title":"GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning","created":"2026-08-31","cited_by_count":1,"area":"lr"}],"next_cursor":null}