{"total":108,"rows":[{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497,"area":"lr"},{"id":"2512.17102","title":"Reinforcement Learning for Self-Improving Agent with Skill Library","created":"2025-12-18","cited_by_count":100,"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":"2604.10674","title":"Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents","created":"2026-04-12","cited_by_count":90,"area":"agents"},{"id":"2505.11821","title":"Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit Assignment","created":"2025-05-17","cited_by_count":79,"area":"lr"},{"id":"2510.24701","title":"Tongyi DeepResearch Technical Report","created":"2025-10-28","cited_by_count":66,"area":"agents"},{"id":"2510.04206","title":"AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework","created":"2025-10-05","cited_by_count":62,"area":"agents"},{"id":"2509.13305","title":"WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning","created":"2025-09-16","cited_by_count":61,"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":"2504.11543","title":"REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites","created":"2025-04-15","cited_by_count":45,"area":"agents"},{"id":"2601.22060","title":"Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models","created":"2026-01-29","cited_by_count":37,"area":"mllm"},{"id":"2605.06130","title":"Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2506.03610","title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","created":"2025-06-04","cited_by_count":31,"area":"agents"},{"id":"2503.00897","title":"A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning","created":"2025-03-02","cited_by_count":30,"area":"diffusion"},{"id":"2510.20022","title":"SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph","created":"2025-10-22","cited_by_count":28,"area":"agents"},{"id":"2606.15912","title":"On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents","created":"2026-06-14","cited_by_count":27,"area":"distill"},{"id":"2604.11978","title":"The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break","created":"2026-04-13","cited_by_count":25,"area":"agents"},{"id":"2605.07725","title":"SOD: Step-wise On-policy Distillation for Small Language Model Agents","created":"2026-05-08","cited_by_count":21,"area":"agents"},{"id":"2511.01331","title":"RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models","created":"2025-11-03","cited_by_count":18,"area":"vla"},{"id":"2602.16165","title":"HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents","created":"2026-02-18","cited_by_count":18,"area":"agents"},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2603.08561","title":"RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback","created":"2026-03-09","cited_by_count":17,"area":null},{"id":"2601.08323","title":"AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation","created":"2026-01-13","cited_by_count":15,"area":"agents"},{"id":"2506.00320","title":"Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents","created":"2025-05-31","cited_by_count":14,"area":"wm"},{"id":"2506.02918","title":"World Modelling Improves Language Model Agents","created":"2025-06-03","cited_by_count":14,"area":"wm"},{"id":"2512.04535","title":"GTM: Simulating the World of Tools for AI Agents","created":"2025-12-04","cited_by_count":14,"area":"agents"},{"id":"2606.03108","title":"EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning","created":"2026-06-02","cited_by_count":14,"area":"agents"},{"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":"2506.05333","title":"Kinetics: Rethinking Test-Time Scaling Laws","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2604.18240","title":"AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation","created":"2026-04-20","cited_by_count":12,"area":"agents"},{"id":"2603.11682","title":"Entropy-Preserving Reinforcement Learning","created":"2026-03-12","cited_by_count":11,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2508.16481","title":"Benchmarking the Robustness of Agentic Systems to Adversarially-Induced Harms","created":"2025-08-22","cited_by_count":10,"area":"agents"},{"id":"2605.13217","title":"GAGPO: Generalized Advantage Grouped Policy Optimization","created":"2026-05-13","cited_by_count":9,"area":"agents"},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2602.11541","title":"Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use","created":"2026-02-12","cited_by_count":8,"area":"agents"},{"id":"2505.23816","title":"A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs","created":"2025-05-27","cited_by_count":7,"area":"lr"},{"id":"2509.25779","title":"Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs","created":"2025-09-30","cited_by_count":7,"area":"agents"},{"id":"2510.07248","title":"Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2512.22733","title":"FoldAct: Efficient and Stable Context Folding for Long-Horizon Search Agents","created":"2025-12-28","cited_by_count":6,"area":"agents"},{"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":"2605.14089","title":"SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration","created":"2026-05-13","cited_by_count":6,"area":"agents"},{"id":"2606.02355","title":"SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training","created":"2026-06-01","cited_by_count":6,"area":"agents"},{"id":"2510.23856","title":"From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Production","created":"2025-10-27","cited_by_count":5,"area":null},{"id":"2603.10101","title":"CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR","created":"2026-03-10","cited_by_count":5,"area":"lr"},{"id":"2605.14558","title":"Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy","created":"2026-05-14","cited_by_count":5,"area":"lr"},{"id":"2609.04094","title":"DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training","created":"2026-09-03","cited_by_count":5,"area":null},{"id":"2506.13109","title":"Leveraging In-Context Learning for Language Model Agents","created":"2025-06-16","cited_by_count":4,"area":"agents"},{"id":"2508.04280","title":"Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success","created":"2025-08-06","cited_by_count":4,"area":"mllm"},{"id":"2510.20909","title":"Code-enabled language models can outperform reasoning models on diverse tasks","created":"2025-10-23","cited_by_count":4,"area":"lr"},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2602.17547","title":"KLong: Training LLM Agent for Extremely Long-horizon Tasks","created":"2026-02-19","cited_by_count":4,"area":"agents"},{"id":"2603.12011","title":"Can RL Improve Generalization of LLM Agents? An Empirical Study","created":"2026-03-12","cited_by_count":4,"area":"agents"},{"id":"2509.23870","title":"Gradient Coupling: The Hidden Barrier to Generalization in Agentic Reinforcement Learning","created":"2025-09-28","cited_by_count":3,"area":"agents"},{"id":"2604.07645","title":"PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent","created":"2026-04-08","cited_by_count":3,"area":"agents"},{"id":"2605.20061","title":"Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents","created":"2026-05-19","cited_by_count":3,"area":"agents"},{"id":"2606.08867","title":"Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Framework","created":"2026-06-07","cited_by_count":3,"area":"agents"},{"id":"2607.02431","title":"WorldSample: Closed-loop Real-robot RL with World Modelling","created":"2026-07-02","cited_by_count":3,"area":"wm"},{"id":"2608.01667","title":"TCPO: Turn-Level Credit Policy Optimization","created":"2026-08-03","cited_by_count":3,"area":"lr"},{"id":"2608.03223","title":"Agentic Reinforcement Learning with Self-Distilled Reward Shaping","created":"2026-08-04","cited_by_count":3,"area":"agents"},{"id":"2601.05787","title":"From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation","created":"2026-01-09","cited_by_count":2,"area":"agents"},{"id":"2602.11351","title":"Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization","created":"2026-02-11","cited_by_count":2,"area":"agents"},{"id":"2602.19000","title":"MagicAgent: Towards Generalized Agent Planning","created":"2026-02-22","cited_by_count":2,"area":"agents"},{"id":"2604.07341","title":"ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories","created":"2026-04-08","cited_by_count":2,"area":"agents"},{"id":"2604.26733","title":"FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards","created":"2026-04-29","cited_by_count":2,"area":"agents"},{"id":"2607.25816","title":"Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL","created":"2026-07-28","cited_by_count":2,"area":"lr"},{"id":"2608.06861","title":"Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents","created":"2026-08-07","cited_by_count":2,"area":"agents"},{"id":"2509.04508","title":"ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models","created":"2025-09-02","cited_by_count":1,"area":"agents"},{"id":"2602.10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2604.03098","title":"Co-Evolution of Policy and Internal Reward for Language Agents","created":"2026-04-03","cited_by_count":1,"area":"agents"},{"id":"2605.06957","title":"Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2605.12131","title":"Rollout Cards: A Reproducibility Standard for Agent Research","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.19762","title":"What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2606.16733","title":"A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2607.23605","title":"Hybrid Advantage Estimation with Unified Critic for VLM Agentic Reinforcement Learning","created":"2026-07-26","cited_by_count":1,"area":"mllm"},{"id":"2608.02650","title":"HyperAgent: Planning and Acting over Tool-Schema Hypergraphs for Tool-Use LLM Agents","created":"2026-07-31","cited_by_count":1,"area":"agents"},{"id":"2608.03499","title":"WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.07147","title":"DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training","created":"2026-08-07","cited_by_count":1,"area":"agents"},{"id":"2608.08255","title":"Learning from Environmental Feedback: Credit Assignment across Multiple Timescales for Agentic Reinforcement Learning","created":"2026-08-08","cited_by_count":1,"area":"agents"},{"id":"2608.09555","title":"Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.11967","title":"LoongReflect: Boosting Long-Horizon Reflection in Search Agents via Global Perspective Distillation","created":"2026-08-12","cited_by_count":1,"area":"agents"},{"id":"2609.02042","title":"Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents","created":"2026-09-02","cited_by_count":1,"area":"agents"},{"id":"2509.01720","title":"Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control","created":"2025-09-01","cited_by_count":0,"area":"alignment"},{"id":"2602.20979","title":"Toward an Agentic Infused Software Ecosystem","created":"2026-02-24","cited_by_count":0,"area":"agents"},{"id":"2604.11465","title":"Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large Agents","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2605.25384","title":"GeoMathCode: Understanding Interleaved Math-Code Reasoning for Geometry Problem Solving","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2606.17735","title":"Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2606.26918","title":"Diagnosing Task Insensitivity in Language Agents","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2607.01897","title":"Rank-Then-Act: Reward-Free Control from Frame-Order Progress","created":"2026-07-02","cited_by_count":0,"area":"alignment"},{"id":"2607.03025","title":"Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.16062","title":"When Model Merging Rivals Joint Multi-Task Reinforcement Learning: A Task-Vector Geometry Analysis","created":"2026-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2608.15041","title":"LLM-Based Hierarchical Coordinated Control with Continuation-Aware Policy Learning","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2609.01245","title":"Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.08404","title":"Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.24115","title":"EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.25678","title":"Toolcompass: Guiding Tool Trialing, Not Suppressing It","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.27532","title":"ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.34054","title":"PReCache: Efficient KV Cache Sharing for Multi-LoRA Agents via Low-Rank Precomputation and Neutral Reconstruction","created":"2026-09-28","cited_by_count":0,"area":"inference"},{"id":"2609.34649","title":"Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.34988","title":"The Right Lesson at the Right Step: Deriving Control Updates for Self-Evolving Agents","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":"100"}