{"total":23,"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":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2405.11804","title":"(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts","created":"2024-05-20","cited_by_count":49,"area":"agents"},{"id":"2605.25338","title":"CausalFlow: Causal Attribution and Counterfactual Repair for LLM Agent Failures","created":"2026-05-25","cited_by_count":18,"area":"agents"},{"id":"2412.11167","title":"Cultural Palette: Pluralising Culture Alignment via Multi-agent Palette","created":"2024-12-15","cited_by_count":16,"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":"2510.06674","title":"Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support","created":"2025-10-08","cited_by_count":10,"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":"2602.08335","title":"Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent System","created":"2026-02-09","cited_by_count":7,"area":"agents"},{"id":"2605.29794","title":"SkillsInjector: Dynamic Skill Context Construction for LLM Agents","created":"2026-05-28","cited_by_count":6,"area":"agents"},{"id":"2607.05441","title":"PORTS: Preference-Optimized Retrievers for Tool Selection with Large Language Models","created":"2026-07-03","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":"2509.23188","title":"Diagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction Conflicts","created":"2025-09-27","cited_by_count":3,"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":"2603.04636","title":"When Agents Persuade: Rhetoric Generation and Mitigation in LLMs","created":"2026-03-04","cited_by_count":1,"area":"agents"},{"id":"2512.18622","title":"A Multi-agent Text2SQL Framework using Small Language Models and Execution Feedback","created":"2025-12-21","cited_by_count":0,"area":"agents"},{"id":"2604.12666","title":"From Imitation to Discrimination: Progressive Curriculum Learning for Robust Web Navigation","created":"2026-04-14","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":"2609.05758","title":"From Monolithic Blending to Agentic Orchestration: Dynamic Response for Conversational Assistants at Scale","created":"2026-09-04","cited_by_count":0,"area":"agents"}],"next_cursor":null}