{"total":45,"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":"2505.22648","title":"WebDancer: Towards Autonomous Information Seeking Agency","created":"2025-05-28","cited_by_count":188,"area":"agents"},{"id":"2604.04804","title":"SkillX: Automatically Constructing Skill Knowledge Bases for Agents","created":"2026-04-06","cited_by_count":76,"area":"agents"},{"id":"2508.04652","title":"LLM Collaboration With Multi-Agent Reinforcement Learning","created":"2025-08-06","cited_by_count":49,"area":"agents"},{"id":"2603.24477","title":"Composer 2 Technical Report","created":"2026-03-25","cited_by_count":22,"area":"agents"},{"id":"2505.13909","title":"Efficient Agent Training for Computer Use","created":"2025-05-20","cited_by_count":18,"area":"agents"},{"id":"2602.14093","title":"GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training","created":"2026-02-15","cited_by_count":18,"area":"agents"},{"id":"2507.14201","title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","created":"2025-07-14","cited_by_count":15,"area":"agents"},{"id":"2605.18703","title":"EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL","created":"2026-05-18","cited_by_count":14,"area":"agents"},{"id":"2509.14480","title":"Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents","created":"2025-09-17","cited_by_count":12,"area":"agents"},{"id":"2509.25084","title":"Scaling Generalist Data-Analytic Agents","created":"2025-09-29","cited_by_count":11,"area":"agents"},{"id":"2510.24397","title":"APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training","created":"2025-10-28","cited_by_count":11,"area":"agents"},{"id":"2601.20209","title":"Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning","created":"2026-01-28","cited_by_count":11,"area":"agents"},{"id":"2603.02045","title":"Expanding LLM Agent Boundaries with Strategy-Guided Exploration","created":"2026-03-02","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":"2505.07184","title":"Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs","created":"2025-05-12","cited_by_count":5,"area":"agents"},{"id":"2512.04949","title":"CARL: Criticality-Aware Agentic Reinforcement Learning","created":"2025-12-04","cited_by_count":5,"area":"agents"},{"id":"2604.02345","title":"UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics","created":"2026-02-11","cited_by_count":5,"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":"2512.22322","title":"SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents","created":"2025-12-26","cited_by_count":3,"area":"agents"},{"id":"2601.07782","title":"Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning","created":"2026-01-12","cited_by_count":3,"area":"agents"},{"id":"2603.16161","title":"SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation","created":"2026-03-17","cited_by_count":3,"area":"agents"},{"id":"2608.17310","title":"Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements","created":"2026-08-18","cited_by_count":3,"area":"agents"},{"id":"2602.19000","title":"MagicAgent: Towards Generalized Agent Planning","created":"2026-02-22","cited_by_count":2,"area":"agents"},{"id":"2603.07853","title":"SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Plans","created":"2026-03-09","cited_by_count":2,"area":"agents"},{"id":"2604.14877","title":"Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis","created":"2026-04-16","cited_by_count":2,"area":"agents"},{"id":"2605.21240","title":"APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents","created":"2026-05-20","cited_by_count":2,"area":"agents"},{"id":"2607.19450","title":"REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning","created":"2026-07-21","cited_by_count":2,"area":"agents"},{"id":"2608.22631","title":"Learning Generalizable Behaviors for Terminal Agents","created":"2026-08-23","cited_by_count":2,"area":"agents"},{"id":"2608.25756","title":"TailSFT: Filtered Fine-Tuning Improves Post-Training Performance","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2510.03323","title":"Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision","created":"2025-10-01","cited_by_count":1,"area":"agents"},{"id":"2510.04089","title":"SPOGW: a Score-based Preference Optimization method via Group-Wise comparison for workflows","created":"2025-10-05","cited_by_count":1,"area":"agents"},{"id":"2510.17928","title":"EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning","created":"2025-10-20","cited_by_count":1,"area":"agents"},{"id":"2604.11840","title":"Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation","created":"2026-04-12","cited_by_count":1,"area":"agents"},{"id":"2507.21065","title":"AI Pedagogy: Dialogic Social Learning for Artificial Agents","created":"2025-05-25","cited_by_count":0,"area":"agents"},{"id":"2602.00959","title":"Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge Extraction","created":"2026-02-01","cited_by_count":0,"area":"agents"},{"id":"2605.02244","title":"The Conversations Beneath the Code: Triadic Data for Long-Horizon Software Engineering Agents","created":"2026-05-04","cited_by_count":0,"area":"agents"},{"id":"2606.03800","title":"Trading Human Curation for Synthetic Augmentation in RLVR","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2608.18351","title":"Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents","created":"2026-08-18","cited_by_count":0,"area":"agents"},{"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":"2609.38324","title":"Multi-agent discussion gains less when dissent is withheld","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.40221","title":"PhantomEnvironments: Training LLM Agents in Fictional Worlds","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.00890","title":"Cross-Benchmark Transfer from RL on Agentic Coding Tasks","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.06204","title":"Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers","created":"2026-10-05","cited_by_count":0,"area":"agents"}],"next_cursor":null}