{"total":54,"rows":[{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2509.04259","title":"RL's Razor: Why Online Reinforcement Learning Forgets Less","created":"2025-09-04","cited_by_count":176,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2603.24472","title":"Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?","created":"2026-03-25","cited_by_count":103,"area":"lr"},{"id":"2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","created":"2026-04-02","cited_by_count":76,"area":"lr"},{"id":"2511.01824","title":"Simulating Environments with Reasoning Models for Agent Training","created":"2025-11-03","cited_by_count":57,"area":"lr"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2605.06387","title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2406.17271","title":"DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph","created":"2024-06-25","cited_by_count":26,"area":"lr"},{"id":"2402.17882","title":"BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra","created":"2024-02-27","cited_by_count":24,"area":"lr"},{"id":"2404.00450","title":"Planning and Editing What You Retrieve for Enhanced Tool Learning","created":"2024-03-30","cited_by_count":21,"area":"lr"},{"id":"2503.04479","title":"ToolFuzz -- Automated Agent Tool Testing","created":"2025-03-06","cited_by_count":18,"area":"lr"},{"id":"2509.11963","title":"ToolRM: Outcome Reward Models for Tool-Calling Large Language Models","created":"2025-09-15","cited_by_count":17,"area":"lr"},{"id":"2605.28014","title":"ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains","created":"2026-05-27","cited_by_count":17,"area":"lr"},{"id":"2407.18553","title":"REAPER: Reasoning based Retrieval Planning for Complex RAG Systems","created":"2024-07-26","cited_by_count":16,"area":"lr"},{"id":"2309.10814","title":"Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning","created":"2023-09-19","cited_by_count":15,"area":"lr"},{"id":"2504.14597","title":"a1: Steep Test-time Scaling Law via Environment Augmented Generation","created":"2025-04-20","cited_by_count":13,"area":"lr"},{"id":"2412.08054","title":"Federated In-Context LLM Agent Learning","created":"2024-12-11","cited_by_count":10,"area":"lr"},{"id":"2606.01039","title":"OPD+: Rethinking the Advantage Design for On-Policy Distillation","created":"2026-05-31","cited_by_count":8,"area":"lr"},{"id":"2408.13863","title":"CodeGraph: Enhancing Graph Reasoning of LLMs with Code","created":"2024-08-25","cited_by_count":6,"area":"lr"},{"id":"2411.04535","title":"Meta-Reasoning Improves Tool Use in Large Language Models","created":"2024-11-07","cited_by_count":6,"area":"lr"},{"id":"2602.09598","title":"Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning","created":"2026-02-10","cited_by_count":6,"area":"lr"},{"id":"2412.14780","title":"Disentangling Reasoning Tokens and Boilerplate Tokens For Language Model Fine-tuning","created":"2024-12-19","cited_by_count":5,"area":"lr"},{"id":"2407.07778","title":"WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment","created":"2024-07-10","cited_by_count":4,"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":"2603.03640","title":"MistyPilot: An Agentic Fast-Slow Thinking LLM Framework for Misty Social Robots","created":"2026-03-04","cited_by_count":3,"area":"lr"},{"id":"2404.11978","title":"EVIT: Event-Oriented Instruction Tuning for Event Reasoning","created":"2024-04-18","cited_by_count":2,"area":"lr"},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2602.01709","title":"ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2605.18529","title":"AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment","created":"2026-05-18","cited_by_count":2,"area":"lr"},{"id":"2605.25443","title":"Harmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning Models","created":"2026-05-25","cited_by_count":2,"area":"lr"},{"id":"2605.27765","title":"Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning","created":"2026-05-26","cited_by_count":2,"area":"lr"},{"id":"2510.08567","title":"MATRIX: Multimodal Agent Tuning for Robust Tool-Use Reasoning","created":"2025-10-09","cited_by_count":1,"area":"lr"},{"id":"2510.12218","title":"GOAT: A Training Framework for Goal-Oriented Agent with Tools","created":"2025-10-14","cited_by_count":1,"area":"lr"},{"id":"2602.02405","title":"Making Expert Reasoning Learnable with Self-Distillation","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2604.03057","title":"Querying Structured Data Through Natural Language Using Language Models","created":"2026-04-03","cited_by_count":1,"area":"lr"},{"id":"2605.22177","title":"Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles","created":"2026-05-21","cited_by_count":1,"area":"lr"},{"id":"2510.06825","title":"Adaptive Tool Generation with Models as Tools and Reinforcement Learning","created":"2025-10-08","cited_by_count":0,"area":"lr"},{"id":"2604.10788","title":"TInR: Exploring Tool-Internalized Reasoning in Large Language Models","created":"2026-04-12","cited_by_count":0,"area":"lr"},{"id":"2605.29568","title":"DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.15589","title":"Is Code Better Than Language for Algorithmic Reasoning","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2607.22639","title":"TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2608.09745","title":"SR-OPSD: Self-Referenced On-Policy Self-Distillation","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2608.11674","title":"GCPO: Diagnosing and Constraining Subspace Geometry in Rollout RL for LLMs","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2608.21863","title":"HiDiffTIR: Hierarchical Difficulty-Aware Policy Optimization for Multi-Turn Tool-Integrated Reasoning","created":"2026-08-22","cited_by_count":0,"area":"lr"},{"id":"2609.06100","title":"VERPO: Verified Evidence Regularized Policy Optimization","created":"2026-09-05","cited_by_count":0,"area":"lr"},{"id":"2609.22194","title":"A Pinch of SFT, A Dash of RL: When Reinforcement Learning Helps Long-Horizon Advertising Agents","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.25618","title":"Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.33181","title":"SeOPD: Self-Evolving LLMs via Online Policy Distillation from Self-Generated Chain-of-Thought","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.36742","title":"SIPO: Unifying Reinforcement Learning with On-Policy Self-Distillation","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.04158","title":"How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.14736","title":"Think in Strategies, Act with Tools: Traceable Agentic Optimization for Combinatorial Problems","created":"2026-10-10","cited_by_count":0,"area":"lr"},{"id":"2610.19687","title":"Function-Space Temporal Self-Distillation for Policy Optimization","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}