{"total":32,"rows":[{"id":"2510.14545","title":"Agentic Entropy-Balanced Policy Optimization","created":"2025-10-16","cited_by_count":40,"area":"agents"},{"id":"2511.14460","title":"Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning","created":"2025-11-18","cited_by_count":29,"area":"agents"},{"id":"2603.21383","title":"PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost","created":"2026-03-22","cited_by_count":14,"area":"agents"},{"id":"2604.28138","title":"Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes","created":"2026-04-30","cited_by_count":13,"area":"agents"},{"id":"2608.01964","title":"LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks","created":"2026-08-03","cited_by_count":13,"area":"agents"},{"id":"2605.10913","title":"Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces","created":"2026-05-11","cited_by_count":12,"area":"agents"},{"id":"2606.11119","title":"TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning","created":"2026-06-09","cited_by_count":10,"area":"agents"},{"id":"2602.01664","title":"FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing","created":"2026-02-02","cited_by_count":9,"area":"agents"},{"id":"2603.06859","title":"Exact Is Easier: Credit Assignment for Cooperative LLM Agents","created":"2026-03-06","cited_by_count":9,"area":"agents"},{"id":"2601.21972","title":"Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic","created":"2026-01-29","cited_by_count":8,"area":"agents"},{"id":"2602.08401","title":"On Protecting Agentic Systems' Intellectual Property via Watermarking","created":"2026-02-09","cited_by_count":8,"area":"agents"},{"id":"2604.18401","title":"CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities","created":"2026-04-20","cited_by_count":8,"area":"agents"},{"id":"2602.11767","title":"TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents","created":"2026-02-12","cited_by_count":7,"area":"agents"},{"id":"2605.05007","title":"Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation","created":"2026-05-06","cited_by_count":6,"area":"agents"},{"id":"2605.14089","title":"SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration","created":"2026-05-13","cited_by_count":6,"area":"agents"},{"id":"2511.00413","title":"Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse","created":"2025-11-01","cited_by_count":5,"area":"agents"},{"id":"2605.06642","title":"StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2605.12004","title":"Learning Agentic Policy from Action Guidance","created":"2026-05-12","cited_by_count":4,"area":"agents"},{"id":"2605.28814","title":"Self-Improving Language Models with Bidirectional Evolutionary Search","created":"2026-05-27","cited_by_count":4,"area":"agents"},{"id":"2606.12384","title":"APPO: Agentic Procedural Policy Optimization","created":"2026-06-10","cited_by_count":4,"area":"agents"},{"id":"2608.28281","title":"LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering","created":"2026-08-28","cited_by_count":3,"area":"agents"},{"id":"2607.06223","title":"Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents","created":"2026-07-07","cited_by_count":2,"area":"agents"},{"id":"2605.04811","title":"Tree-based Credit Assignment for Multi-Agent Memory System","created":"2026-05-06","cited_by_count":1,"area":"agents"},{"id":"2609.21378","title":"ArenaFlow: From Trajectory Ranking to Hierarchical Credit Propagation for Open-Ended Agent RL","created":"2026-09-18","cited_by_count":1,"area":"agents"},{"id":"2609.22258","title":"RS-Claw-Evolution: Environment-Feedback-Driven Evolution for Lightweight Remote Sensing Agents in Long-Horizon Tasks","created":"2026-09-06","cited_by_count":0,"area":"agents"},{"id":"2609.33875","title":"Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.35215","title":"ASCT: Attentive Search over Counterfactual Trees for Credit Assignment in Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.37898","title":"Guide, Then Let Go: Gap-Adaptive Teacher Scheduling for Sparse-Reward Agentic RL","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.39154","title":"DAGent: Evaluate-then-Grow Planning for Deep Research Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.01207","title":"Dependency-Aware Reward Shaping for Agentic Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.02525","title":"Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.20334","title":"TreeFlex: Agents Navigating Their Own Search Trees","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}