{"total":263,"rows":[{"id":"2508.06471","title":"GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models","created":"2025-08-08","cited_by_count":467,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"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":"2509.02479","title":"SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning","created":"2025-09-02","cited_by_count":146,"area":"lr"},{"id":"2508.20453","title":"MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers","created":"2025-08-28","cited_by_count":109,"area":"agents"},{"id":"2511.13646","title":"Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?","created":"2025-11-17","cited_by_count":95,"area":"agents"},{"id":"2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","created":"2025-08-15","cited_by_count":91,"area":"lr"},{"id":"2603.11137","title":"Scaling Reasoning Efficiently via Relaxed On-Policy Distillation","created":"2026-03-11","cited_by_count":82,"area":"lr"},{"id":"2510.11370","title":"Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers","created":"2025-10-13","cited_by_count":72,"area":"moe"},{"id":"2604.12002","title":"Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision","created":"2026-04-13","cited_by_count":68,"area":"distill"},{"id":"2510.26788","title":"Defeating the Training-Inference Mismatch via FP16","created":"2025-10-30","cited_by_count":66,"area":null},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59,"area":"agents"},{"id":"2508.08221","title":"Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning","created":"2025-08-11","cited_by_count":56,"area":"lr"},{"id":"2507.19427","title":"Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding","created":"2025-07-25","cited_by_count":55,"area":"moe"},{"id":"2508.20722","title":"rStar2-Agent: Agentic Reasoning Technical Report","created":"2025-08-28","cited_by_count":54,"area":"lr"},{"id":"2508.15763","title":"Intern-S1: A Scientific Multimodal Foundation Model","created":"2025-08-21","cited_by_count":53,"area":"moe"},{"id":"2510.01161","title":"Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?","created":"2025-10-01","cited_by_count":53,"area":"lr"},{"id":"2602.02482","title":"Expanding the Capabilities of Reinforcement Learning via Text Feedback","created":"2026-02-02","cited_by_count":53,"area":"alignment"},{"id":"2512.13607","title":"Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models","created":"2025-12-15","cited_by_count":48,"area":"lr"},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2509.23045","title":"Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents","created":"2025-09-27","cited_by_count":41,"area":"agents"},{"id":"2512.01374","title":"Stabilizing Reinforcement Learning with LLMs: Formulation and Practices","created":"2025-12-01","cited_by_count":41,"area":"moe"},{"id":"2512.18552","title":"Toward Training Superintelligent Software Agents through Self-Play SWE-RL","created":"2025-12-21","cited_by_count":40,"area":"agents"},{"id":"2508.07629","title":"Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization","created":"2025-08-11","cited_by_count":39,"area":"lr"},{"id":"2602.04879","title":"Rethinking the Trust Region in LLM Reinforcement Learning","created":"2026-02-04","cited_by_count":37,"area":"lr"},{"id":"2509.04419","title":"Towards a Unified View of Large Language Model Post-Training","created":"2025-09-04","cited_by_count":36,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2604.13010","title":"Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation","created":"2026-04-14","cited_by_count":33,"area":"lr"},{"id":"2606.23321","title":"Tmax: A simple recipe for terminal agents","created":"2026-06-22","cited_by_count":33,"area":"agents"},{"id":"2507.11407","title":"EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes","created":"2025-07-15","cited_by_count":32,"area":"lr"},{"id":"2509.13232","title":"Single-stream Policy Optimization","created":"2025-09-16","cited_by_count":28,"area":"lr"},{"id":"2508.02669","title":"MedVLThinker: Simple Baselines for Multimodal Medical Reasoning","created":"2025-08-04","cited_by_count":27,"area":"lr"},{"id":"2602.13035","title":"Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL","created":"2026-02-13","cited_by_count":27,"area":null},{"id":"2605.07865","title":"KL for a KL: On-Policy Distillation with Control Variate Baseline","created":"2026-05-08","cited_by_count":26,"area":"lr"},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2510.06062","title":"When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL","created":"2025-10-07","cited_by_count":21,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2508.08636","title":"InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scaling","created":"2025-08-12","cited_by_count":20,"area":"lr"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2604.09852","title":"MEMENTO: Teaching LLMs to Manage Their Own Context","created":"2026-04-10","cited_by_count":18,"area":"lr"},{"id":"2602.04663","title":"Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design","created":"2026-02-04","cited_by_count":17,"area":"lr"},{"id":"2608.06296","title":"On-Policy Self-Distillation without Any Supervision","created":"2026-08-06","cited_by_count":17,"area":"lr"},{"id":"2510.04474","title":"DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","cited_by_count":16,"area":"lr"},{"id":"2602.20739","title":"PyVision-RL: Forging Open Agentic Vision Models via RL","created":"2026-02-24","cited_by_count":16,"area":"agents"},{"id":"2509.24203","title":"Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"id":"2510.11345","title":"Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony","created":"2025-10-13","cited_by_count":15,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"id":"2507.16577","title":"Scaling Linear Attention with Sparse State Expansion","created":"2025-07-22","cited_by_count":13,"area":null},{"id":"2509.20241","title":"Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling","created":"2025-09-24","cited_by_count":13,"area":null},{"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":"2602.21534","title":"ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning","created":"2026-02-25","cited_by_count":13,"area":"agents"},{"id":"2510.08141","title":"SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2510.08308","title":"First Try Matters: Revisiting the Role of Reflection in Reasoning Models","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2602.21611","title":"Structurally Aligned Subtask-Level Memory for Software Engineering Agents","created":"2026-02-25","cited_by_count":12,"area":"agents"},{"id":"2603.04257","title":"Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory","created":"2026-03-04","cited_by_count":12,"area":"agents"},{"id":"2511.17729","title":"M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark","created":"2025-11-21","cited_by_count":11,"area":"agents"},{"id":"2511.21016","title":"Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression","created":"2025-11-26","cited_by_count":11,"area":null},{"id":"2512.15649","title":"VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?","created":"2025-12-17","cited_by_count":11,"area":"mllm"},{"id":"2602.06717","title":"F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare","created":"2026-02-06","cited_by_count":11,"area":"lr"},{"id":"2602.07774","title":"GR2: Generative Reasoning Re-ranker","created":"2026-02-08","cited_by_count":11,"area":"lr"},{"id":"2602.10693","title":"VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training","created":"2026-02-11","cited_by_count":11,"area":"moe"},{"id":"2602.17550","title":"MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2603.26535","title":"PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization","created":"2026-03-27","cited_by_count":11,"area":"lr"},{"id":"2510.01656","title":"Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"id":"2510.19338","title":"Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning","created":"2025-10-22","cited_by_count":10,"area":null},{"id":"2512.08829","title":"InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models","created":"2025-12-09","cited_by_count":10,"area":"mllm"},{"id":"2601.21459","title":"HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing","created":"2026-01-29","cited_by_count":10,"area":"lr"},{"id":"2602.05758","title":"LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards","created":"2026-02-05","cited_by_count":10,"area":"lr"},{"id":"2602.08064","title":"SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm","created":"2026-02-08","cited_by_count":10,"area":null},{"id":"2604.20209","title":"Scaling Self-Play with Self-Guidance","created":"2026-04-22","cited_by_count":10,"area":"synth"},{"id":"2606.02373","title":"Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses","created":"2026-06-01","cited_by_count":10,"area":"lr"},{"id":"2512.00499","title":"ESPO: Entropy Importance Sampling Policy Optimization","created":"2025-11-29","cited_by_count":9,"area":"lr"},{"id":"2602.01826","title":"Beyond Precision: Training-Inference Mismatch is an Optimization Problem and Simple LR Scheduling Fixes It","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2602.15620","title":"STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens","created":"2026-02-17","cited_by_count":9,"area":"lr"},{"id":"2604.26779","title":"Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding","created":"2026-04-29","cited_by_count":9,"area":"inference"},{"id":"2508.20697","title":"Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning","created":"2025-08-28","cited_by_count":8,"area":null},{"id":"2511.06221","title":"Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B","created":"2025-11-09","cited_by_count":8,"area":"lr"},{"id":"2603.09652","title":"MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants","created":"2026-03-10","cited_by_count":8,"area":null},{"id":"2510.12563","title":"HardcoreLogic: Challenging Large Reasoning Models with Long-tail Logic Puzzle Games","created":"2025-10-14","cited_by_count":7,"area":"lr"},{"id":"2601.14952","title":"CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning","created":"2026-01-21","cited_by_count":7,"area":"lr"},{"id":"2601.22718","title":"A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization","created":"2026-01-30","cited_by_count":7,"area":"lr"},{"id":"2605.14220","title":"Diagnosing Training Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2605.17570","title":"How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning","created":"2026-05-17","cited_by_count":7,"area":"lr"},{"id":"2607.01299","title":"HYPIC: Accelerating Hybrid-Attention LLM Serving with Position-Independent Caching","created":"2026-07-01","cited_by_count":7,"area":"rag"},{"id":"2510.23027","title":"Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts","created":"2025-10-27","cited_by_count":6,"area":"lr"},{"id":"2602.12036","title":"Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2605.02572","title":"On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length","created":"2026-05-04","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2606.18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","created":"2026-06-17","cited_by_count":6,"area":"lr"},{"id":"2511.04256","title":"SSPO: Subsentence-level Policy Optimization","created":"2025-11-06","cited_by_count":5,"area":"lr"},{"id":"2601.23135","title":"Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2602.04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2602.14697","title":"Evolutionary System Prompt Learning for Reinforcement Learning in LLMs","created":"2026-02-16","cited_by_count":5,"area":"agents"},{"id":"2602.22675","title":"Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization","created":"2026-02-26","cited_by_count":5,"area":"agents"},{"id":"2603.16140","title":"Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards","created":"2026-03-17","cited_by_count":5,"area":null},{"id":"2603.17621","title":"Complementary RL: Towards Efficient Experience-Driven Agent Learning","created":"2026-03-18","cited_by_count":5,"area":"agents"},{"id":"2604.17654","title":"Poly-EPO: Training Exploratory Reasoning Models","created":"2026-04-19","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"}],"next_cursor":"100"}