{"total":33,"rows":[{"id":"2504.13958","title":"ToolRL: Reward is All Tool Learning Needs","created":"2025-04-16","cited_by_count":362,"area":"agents"},{"id":"2406.14868","title":"Direct Multi-Turn Preference Optimization for Language Agents","created":"2024-06-21","cited_by_count":64,"area":"agents"},{"id":"2502.04306","title":"ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization","created":"2025-02-06","cited_by_count":56,"area":"agents"},{"id":"2509.19736","title":"UserRL: Training Interactive User-Centric Agent via Reinforcement Learning","created":"2025-09-24","cited_by_count":32,"area":"agents"},{"id":"2501.01821","title":"SDPO: Segment-Level Direct Preference Optimization for Social Agents","created":"2025-01-03","cited_by_count":30,"area":"agents"},{"id":"2510.08529","title":"CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards","created":"2025-10-09","cited_by_count":29,"area":"agents"},{"id":"2410.07672","title":"MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization","created":"2024-10-10","cited_by_count":22,"area":"agents"},{"id":"2509.12867","title":"Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use","created":"2025-09-16","cited_by_count":16,"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":"2501.14225","title":"Multi-agent KTO: Reinforcing Strategic Interactions of Large Language Model in Language Game","created":"2025-01-24","cited_by_count":10,"area":"agents"},{"id":"2505.19428","title":"Frictional Agent Alignment Framework: Slow Down and Don't Break Things","created":"2025-05-26","cited_by_count":10,"area":"agents"},{"id":"2412.17061","title":"Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration","created":"2024-12-22","cited_by_count":9,"area":"agents"},{"id":"2411.13904","title":"Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning","created":"2024-11-21","cited_by_count":7,"area":"agents"},{"id":"2502.20757","title":"The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents","created":"2025-02-28","cited_by_count":7,"area":"agents"},{"id":"2509.05882","title":"Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes","created":"2025-09-07","cited_by_count":7,"area":"agents"},{"id":"2601.14230","title":"MASCOT: Multi-Agent Socio-Collaborative Companion Systems","created":"2026-01-20","cited_by_count":7,"area":"agents"},{"id":"2506.14302","title":"Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent","created":"2025-06-17","cited_by_count":4,"area":"agents"},{"id":"2510.04695","title":"Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents","created":"2025-10-06","cited_by_count":4,"area":"agents"},{"id":"2604.05339","title":"Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities","created":"2026-04-07","cited_by_count":4,"area":"agents"},{"id":"2607.09375","title":"Mach-Mind-4-Flash Technical Report","created":"2026-07-10","cited_by_count":4,"area":"agents"},{"id":"2607.10601","title":"Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories","created":"2026-07-12","cited_by_count":4,"area":"agents"},{"id":"2510.22462","title":"Learning \"Partner-Aware\" Collaborators in Multi-Party Collaboration","created":"2025-10-26","cited_by_count":2,"area":"agents"},{"id":"2604.11259","title":"Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization","created":"2026-04-13","cited_by_count":2,"area":"agents"},{"id":"2503.11346","title":"AIstorian lets AI be a historian: A KG-powered multi-agent system for accurate biography generation","created":"2025-03-14","cited_by_count":1,"area":"agents"},{"id":"2602.10490","title":"ChainRec: An Agentic Recommender Learning to Route Tool Chains for Diverse and Evolving Interests","created":"2026-02-11","cited_by_count":1,"area":"agents"},{"id":"2602.22697","title":"Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue","created":"2026-02-26","cited_by_count":1,"area":"agents"},{"id":"2605.16471","title":"From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI","created":"2026-05-15","cited_by_count":0,"area":"agents"},{"id":"2608.29357","title":"LiteSearch-VL: Small Multimodal Search Agents via Trajectory Distillation and Synthetic Step-DPO","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2609.05513","title":"When and What to Teach: Budget-Aware Online Adaptation for Web Agents","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.32827","title":"Improving LLM Collaboration via Multi-Agent Preference Learning","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.39551","title":"RankEvolve: A Reliable Multi-Agent Auto-Research Harness for Evolving Ranking Models","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.13755","title":"Matched-Context Group Policy Optimization for LLM Agent Training","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.19439","title":"Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}