{"total":64,"rows":[{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124,"area":null},{"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":"2501.11425","title":"Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training","created":"2025-01-20","cited_by_count":82,"area":"lr"},{"id":"2502.06772","title":"ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates","created":"2025-02-10","cited_by_count":63,"area":"lr"},{"id":"2503.22458","title":"Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey","created":"2025-03-28","cited_by_count":57,"area":"agents"},{"id":"2503.12434","title":"A Survey on the Optimization of Large Language Model-based Agents","created":"2025-03-16","cited_by_count":46,"area":"agents"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2506.21656","title":"Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs","created":"2025-06-26","cited_by_count":32,"area":"lr"},{"id":"2501.01821","title":"SDPO: Segment-Level Direct Preference Optimization for Social Agents","created":"2025-01-03","cited_by_count":30,"area":"agents"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2503.16024","title":"The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement","created":"2025-03-20","cited_by_count":20,"area":"lr"},{"id":"2504.21561","title":"Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning","created":"2025-04-30","cited_by_count":19,"area":"mllm"},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2604.06185","title":"Benchmarking LLM Tool-Use in the Wild","created":"2026-02-13","cited_by_count":17,"area":null},{"id":"2506.02918","title":"World Modelling Improves Language Model Agents","created":"2025-06-03","cited_by_count":14,"area":"wm"},{"id":"2507.07441","title":"SAND: Boosting LLM Agents with Self-Taught Action Deliberation","created":"2025-07-10","cited_by_count":14,"area":"agents"},{"id":"2512.07761","title":"TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards","created":"2025-12-08","cited_by_count":14,"area":"safety"},{"id":"2504.02623","title":"Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions","created":"2025-04-03","cited_by_count":12,"area":"agents"},{"id":"2508.19504","title":"Aegis: Taxonomy and Optimizations for Overcoming Agent-Environment Failures in LLM Agents","created":"2025-08-27","cited_by_count":10,"area":"agents"},{"id":"2605.09808","title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","created":"2026-05-10","cited_by_count":10,"area":null},{"id":"2603.04783","title":"Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction","created":"2026-03-05","cited_by_count":9,"area":"lr"},{"id":"2504.02882","title":"DiaTool-DPO: Multi-Turn Direct Preference Optimization for Tool-Augmented Large Language Models","created":"2025-04-02","cited_by_count":8,"area":"alignment"},{"id":"2603.02216","title":"ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2605.29559","title":"LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents","created":"2026-05-28","cited_by_count":8,"area":null},{"id":"2602.09138","title":"PABU: Progress-Aware Belief Update for Efficient LLM Agents","created":"2026-02-09","cited_by_count":7,"area":"agents"},{"id":"2603.04949","title":"TimeWarp: Evaluating Web Agents by Revisiting the Past","created":"2026-03-05","cited_by_count":7,"area":"agents"},{"id":"2503.04808","title":"Learning from Failures in Multi-Attempt Reinforcement Learning","created":"2025-03-04","cited_by_count":6,"area":"lr"},{"id":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"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":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2506.02827","title":"TO-GATE: Clarifying Questions and Summarizing Responses with Trajectory Optimization for Eliciting Human Preference","created":"2025-06-03","cited_by_count":5,"area":null},{"id":"2509.25717","title":"Importance Sampling for Multi-Negative Multimodal Direct Preference Optimization","created":"2025-09-30","cited_by_count":5,"area":"mllm"},{"id":"2605.05413","title":"From History to State: Constant-Context Skill Learning for LLM Agents","created":"2026-05-06","cited_by_count":5,"area":"agents"},{"id":"2502.00955","title":"Efficient Multi-Agent System Training with Data Influence-Oriented Tree Search","created":"2025-02-02","cited_by_count":4,"area":"agents"},{"id":"2505.18746","title":"$C^3$-Bench: The Things Real Disturbing LLM based Agent in Multi-Tasking","created":"2025-05-24","cited_by_count":4,"area":"agents"},{"id":"2509.23206","title":"PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness","created":"2025-09-27","cited_by_count":4,"area":"agents"},{"id":"2511.15392","title":"DEPO: Dual-Efficiency Preference Optimization for LLM Agents","created":"2025-11-19","cited_by_count":4,"area":"lr"},{"id":"2605.02943","title":"Healthcare AI GYM for Medical Agents","created":"2026-05-01","cited_by_count":4,"area":"distill"},{"id":"2606.07367","title":"Self-evolving LLM agents with in-distribution Optimization","created":"2026-06-05","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":"2509.23166","title":"Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2510.25441","title":"Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2511.21638","title":"Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF","created":"2025-11-26","cited_by_count":3,"area":"lr"},{"id":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2510.08256","title":"Mix- and MoE-DPO: A Variational Inference Approach to Direct Preference Optimization","created":"2025-10-09","cited_by_count":2,"area":"alignment"},{"id":"2605.24432","title":"Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2605.29256","title":"DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2609.05837","title":"AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories","created":"2026-09-05","cited_by_count":2,"area":"agents"},{"id":"2507.13285","title":"Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesis","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2602.01068","title":"From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization","created":"2026-02-01","cited_by_count":1,"area":"alignment"},{"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":"2608.17605","title":"Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2512.24693","title":"MUSIC: MUlti-Step Instruction Contrast for Multi-Turn Reward Models","created":"2025-12-31","cited_by_count":0,"area":"alignment"},{"id":"2605.26403","title":"From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulator","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.27136","title":"Joint Learning of Experiential Rules and Policies for Large Language Model Agents","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2607.19371","title":"Mitigating Scaffolding Collapse in Socratic Tutors via Representation Alignment","created":"2026-06-15","cited_by_count":0,"area":"alignment"},{"id":"2608.04056","title":"Learning Sexism Detection Using Multi-Agent Perspectivist Preference Optimization","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.10042","title":"UserToolBench: A User-Profile-Hidden Benchmark for Personalized Decision Making in Tool-Use LLMs","created":"2026-08-10","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":"2609.16760","title":"Turn-level Multiscale Density Ratio Estimation for LLM Agents","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.22256","title":"DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues","created":"2026-09-06","cited_by_count":0,"area":"alignment"},{"id":"2609.25678","title":"Toolcompass: Guiding Tool Trialing, Not Suppressing It","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.19376","title":"DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}