{"total":101,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199,"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":"2508.03680","title":"Agent Lightning: Train ANY AI Agents with Reinforcement Learning","created":"2025-08-05","cited_by_count":109,"area":"lr"},{"id":"2509.01055","title":"VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use","created":"2025-09-01","cited_by_count":96,"area":"lr"},{"id":"2603.10165","title":"OpenClaw-RL: Train Any Agent Simply by Talking","created":"2026-03-10","cited_by_count":90,"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":"2602.22817","title":"Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-02-26","cited_by_count":49,"area":"lr"},{"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":"2509.21009","title":"RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training","created":"2025-09-25","cited_by_count":35,"area":"lr"},{"id":"2605.26684","title":"Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning","created":"2026-05-26","cited_by_count":31,"area":"agents"},{"id":"2509.18521","title":"APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation","created":"2025-09-23","cited_by_count":30,"area":"lr"},{"id":"2512.24873","title":"Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem","created":"2025-12-31","cited_by_count":30,"area":"agents"},{"id":"2509.23866","title":"Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation","created":"2025-09-28","cited_by_count":26,"area":"lr"},{"id":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2511.14617","title":"Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning","created":"2025-11-18","cited_by_count":25,"area":null},{"id":"2510.01051","title":"GEM: A Gym for Agentic LLMs","created":"2025-10-01","cited_by_count":23,"area":"agents"},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2601.04786","title":"AgentOCR: Reimagining Agent History via Optical Self-Compression","created":"2026-01-08","cited_by_count":22,"area":"agents"},{"id":"2602.03411","title":"SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training","created":"2026-02-03","cited_by_count":22,"area":"agents"},{"id":"2510.24592","title":"ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization","created":"2025-10-28","cited_by_count":20,"area":"lr"},{"id":"2509.19760","title":"Logics-Parsing Technical Report","created":"2025-09-24","cited_by_count":17,"area":"mllm"},{"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":"2507.06181","title":"CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization","created":"2025-07-08","cited_by_count":16,"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":"2602.08847","title":"Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems","created":"2026-02-09","cited_by_count":16,"area":"lr"},{"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":"2509.06733","title":"Reinforcement Learning Foundations for Deep Research Systems: A Survey","created":"2025-09-08","cited_by_count":14,"area":"lr"},{"id":"2510.01555","title":"Rethinking KL Regularization in RLHF: From Value Estimation to Gradient Optimization","created":"2025-10-02","cited_by_count":14,"area":"alignment"},{"id":"2512.22560","title":"RollArt: Disaggregated Multi-Task Agentic RL Training at Scale","created":"2025-12-27","cited_by_count":14,"area":"agents"},{"id":"2602.01970","title":"Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models","created":"2026-02-02","cited_by_count":14,"area":"lr"},{"id":"2601.18150","title":"FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning","created":"2026-01-26","cited_by_count":13,"area":"inference"},{"id":"2606.22995","title":"Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning","created":"2026-06-22","cited_by_count":13,"area":"agents"},{"id":"2512.06547","title":"A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation","created":"2025-12-06","cited_by_count":12,"area":null},{"id":"2507.22879","title":"RecGPT Technical Report","created":"2025-07-30","cited_by_count":11,"area":null},{"id":"2603.26535","title":"PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization","created":"2026-03-27","cited_by_count":11,"area":"lr"},{"id":"2605.10325","title":"Verifiable Process Rewards for Agentic Reasoning","created":"2026-05-11","cited_by_count":11,"area":"lr"},{"id":"2508.12365","title":"TaoSR1: The Thinking Model for E-commerce Relevance Search","created":"2025-08-17","cited_by_count":10,"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":"2604.02795","title":"Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks","created":"2026-04-03","cited_by_count":10,"area":"alignment"},{"id":"2606.12370","title":"Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling","created":"2026-06-10","cited_by_count":9,"area":null},{"id":"2510.14255","title":"Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization","created":"2025-10-16","cited_by_count":8,"area":"diffusion"},{"id":"2604.11554","title":"Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale","created":"2026-04-13","cited_by_count":7,"area":"lr"},{"id":"2605.20104","title":"Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding","created":"2026-05-19","cited_by_count":6,"area":"inference"},{"id":"2511.17652","title":"TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots","created":"2025-11-20","cited_by_count":5,"area":"lr"},{"id":"2603.01501","title":"GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control","created":"2026-03-02","cited_by_count":5,"area":null},{"id":"2605.12070","title":"Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction","created":"2026-05-12","cited_by_count":5,"area":"agents"},{"id":"2510.08048","title":"TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance","created":"2025-10-09","cited_by_count":4,"area":"alignment"},{"id":"2511.13885","title":"Retrieval-GRPO: A Multi-Objective Reinforcement Learning Framework for Dense Retrieval in Taobao Search","created":"2025-11-17","cited_by_count":4,"area":"lr"},{"id":"2601.01562","title":"Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement","created":"2026-01-04","cited_by_count":4,"area":"lr"},{"id":"2602.08355","title":"E-VAds: An E-commerce Short Videos Understanding Benchmark for MLLMs","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2605.18548","title":"STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics","created":"2026-05-18","cited_by_count":4,"area":"agents"},{"id":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"id":"2511.05589","title":"CoPRIS: Efficient and Stable Reinforcement Learning via Concurrency-Controlled Partial Rollout with Importance Sampling","created":"2025-11-05","cited_by_count":3,"area":"lr"},{"id":"2601.10477","title":"Urban Socio-Semantic Segmentation with Vision-Language Reasoning","created":"2026-01-15","cited_by_count":3,"area":"lr"},{"id":"2602.01103","title":"Probing RLVR training instability through the lens of objective-level hacking","created":"2026-02-01","cited_by_count":3,"area":"lr"},{"id":"2604.16918","title":"Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning","created":"2026-04-18","cited_by_count":3,"area":"lr"},{"id":"2606.10646","title":"How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2512.17206","title":"Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs","created":"2025-12-19","cited_by_count":2,"area":"lr"},{"id":"2601.20327","title":"CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria","created":"2026-01-28","cited_by_count":2,"area":"alignment"},{"id":"2602.09578","title":"Rollout-Training Co-Design for Efficient LLM-Based Multi-Agent Reinforcement Learning","created":"2026-02-10","cited_by_count":2,"area":"agents"},{"id":"2605.30859","title":"DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2608.11878","title":"ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents","created":"2026-08-12","cited_by_count":2,"area":"agents"},{"id":"2608.23283","title":"Apodex 1.1: Scaling Agentic Intelligence for Complex Work","created":"2026-08-24","cited_by_count":2,"area":"agents"},{"id":"2509.15927","title":"Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2510.07685","title":"LiveThinking: Enabling Real-Time Efficient Reasoning for AI-Powered Livestreaming via Reinforcement Learning","created":"2025-10-09","cited_by_count":1,"area":"lr"},{"id":"2510.07972","title":"SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance","created":"2025-10-09","cited_by_count":1,"area":"alignment"},{"id":"2510.26287","title":"Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search","created":"2025-10-30","cited_by_count":1,"area":"agents"},{"id":"2512.21450","title":"RLLaVA: An RL-central Framework for Language and Vision Assistants","created":"2025-12-25","cited_by_count":1,"area":null},{"id":"2512.24957","title":"AMAP Agentic Planning Technical Report","created":"2025-12-31","cited_by_count":1,"area":"agents"},{"id":"2602.18548","title":"1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2603.18464","title":"AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models","created":"2026-03-19","cited_by_count":1,"area":"wm"},{"id":"2604.16893","title":"EasyVideoR1: Easier RL for Video Understanding","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2604.23838","title":"JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training","created":"2026-04-26","cited_by_count":1,"area":null},{"id":"2606.29526","title":"The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2608.08960","title":"Reading is not Reasoning: Bridging the Agentic Policy Gap in Vision-Text Compression","created":"2026-08-09","cited_by_count":1,"area":"agents"},{"id":"2608.14498","title":"Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training","created":"2026-08-14","cited_by_count":1,"area":"mllm"},{"id":"2510.11122","title":"Learning to Trust: Dynamic Utilization of Retrieval-Augmented Generation for E-commerce Search Relevance","created":"2025-10-13","cited_by_count":0,"area":"rag"},{"id":"2511.01470","title":"BARD: budget-aware reasoning distillation","created":"2025-11-03","cited_by_count":0,"area":"lr"},{"id":"2603.19710","title":"AIGQ: An End-to-End Hybrid Generative Architecture for E-commerce Query Recommendation","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2605.04906","title":"Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2605.08766","title":"UserGPT Technical Report","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.04155","title":"SocialCoach: Personalized Social Skill Learning with Agentic Tutoring and Practice","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2606.19004","title":"Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training","created":"2026-06-17","cited_by_count":0,"area":"diffusion"},{"id":"2606.24369","title":"Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.31693","title":"ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping","created":"2026-06-30","cited_by_count":0,"area":"agents"},{"id":"2607.23740","title":"ZenGen: Social Mind for LLMs","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.05832","title":"Enhancing Social Intelligence in LLMs with Hierarchical Reasoning and Utterance-Level Goal Rewarding","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2608.27046","title":"Performance Foundations of Parallel & Distributed Reasoning Language Models","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2609.23377","title":"One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents","created":"2026-09-20","cited_by_count":0,"area":"lr"},{"id":"2609.29892","title":"Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.30837","title":"MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation","created":"2026-09-25","cited_by_count":0,"area":"distill"},{"id":"2609.33848","title":"QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.35158","title":"PEARL: Adaptive Prefill-Decode Execution with Elasticity for Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.39402","title":"Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.03099","title":"Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.09914","title":"RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement Learning","created":"2026-10-07","cited_by_count":0,"area":"lr"},{"id":"2610.16592","title":"Prorsa: Unleashing the Potential of Prefill-Decode Disaggregation in Agentic Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.16866","title":"Efficient Resource-Shiftable RL Post-training with Generative Rewards","created":"2026-10-12","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}