{"total":124,"rows":[{"id":"2510.16907","title":"VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents","created":"2025-10-19","cited_by_count":62,"area":"wm"},{"id":"2511.02208","title":"Training Proactive and Personalized LLM Agents","created":"2025-11-04","cited_by_count":46,"area":"agents"},{"id":"2511.08798","title":"Structured Uncertainty guided Clarification for LLM Agents","created":"2025-11-11","cited_by_count":41,"area":"agents"},{"id":"2603.03303","title":"HumanLM: Simulating Users with State Alignment Beats Response Imitation","created":"2026-02-07","cited_by_count":37,"area":null},{"id":"2505.00753","title":"LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey","created":"2025-05-01","cited_by_count":29,"area":"agents"},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2503.20749","title":"Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data","created":"2025-03-26","cited_by_count":28,"area":"agents"},{"id":"2508.21184","title":"BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design","created":"2025-08-28","cited_by_count":24,"area":null},{"id":"2603.01966","title":"AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations","created":"2026-03-02","cited_by_count":20,"area":null},{"id":"2510.05318","title":"BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions","created":"2025-10-06","cited_by_count":19,"area":null},{"id":"2606.29957","title":"SWE-Together: Evaluating Coding Agents in Interactive User Sessions","created":"2026-06-29","cited_by_count":18,"area":"agents"},{"id":"2602.16699","title":"Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents","created":"2026-02-18","cited_by_count":17,"area":"agents"},{"id":"2507.21389","title":"Teaching Language Models To Gather Information Proactively","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2604.00892","title":"When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation","created":"2026-04-01","cited_by_count":14,"area":"agents"},{"id":"2510.21903","title":"TOM-SWE: User Mental Modeling For Software Engineering Agents","created":"2025-10-24","cited_by_count":13,"area":"agents"},{"id":"2511.02687","title":"The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation","created":"2025-11-04","cited_by_count":13,"area":"agents"},{"id":"2505.22961","title":"ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind","created":"2025-05-29","cited_by_count":12,"area":null},{"id":"2601.06407","title":"Value of Information: A Framework for Human-Agent Communication","created":"2026-01-10","cited_by_count":12,"area":"agents"},{"id":"2603.00656","title":"InfoPO: Information-Driven Policy Optimization for User-Centric Agents","created":"2026-02-28","cited_by_count":12,"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":"2601.09072","title":"Human-AI Co-design for Clinical Prediction Models","created":"2026-01-14","cited_by_count":9,"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":"2509.14404","title":"A Taxonomy of Prompt Defects in LLM Systems","created":"2025-09-17","cited_by_count":8,"area":null},{"id":"2510.06105","title":"Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences","created":"2025-10-07","cited_by_count":8,"area":null},{"id":"2601.21972","title":"Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic","created":"2026-01-29","cited_by_count":8,"area":"agents"},{"id":"2605.16616","title":"MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2601.02702","title":"MultiSessionCollab: Learning User Preferences with Memory to Improve Long-Term Collaboration","created":"2026-01-06","cited_by_count":7,"area":null},{"id":"2602.06714","title":"PrefIx: Understand and Adapt to User Preference in Human-Agent Interaction","created":"2026-02-06","cited_by_count":7,"area":"agents"},{"id":"2603.05923","title":"Learning Next Action Predictors from Human-Computer Interaction","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2508.07955","title":"Expert Preference-based Evaluation of Automated Related Work Generation","created":"2025-08-11","cited_by_count":6,"area":null},{"id":"2602.03429","title":"DiscoverLLM: From Executing Intents to Discovering Them","created":"2026-02-03","cited_by_count":6,"area":null},{"id":"2605.07847","title":"Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors","created":"2026-05-08","cited_by_count":6,"area":null},{"id":"2507.23407","title":"Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaboration","created":"2025-07-31","cited_by_count":5,"area":null},{"id":"2512.04068","title":"Learning Steerable Clarification Policies with Collaborative Self-play","created":"2025-12-03","cited_by_count":5,"area":null},{"id":"2601.10532","title":"PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models","created":"2026-01-15","cited_by_count":5,"area":"alignment"},{"id":"2602.18920","title":"DeepInnovator: Triggering the Innovative Capabilities of LLMs","created":"2026-02-21","cited_by_count":5,"area":"agents"},{"id":"2506.13324","title":"Towards Pervasive Distributed Agentic Generative AI -- A State of The Art","created":"2025-06-16","cited_by_count":4,"area":"agents"},{"id":"2510.12264","title":"Reducing Belief Deviation in Reinforcement Learning for Active Reasoning","created":"2025-10-14","cited_by_count":4,"area":"lr"},{"id":"2510.18413","title":"Adamas: Hadamard Sparse Attention for Efficient Long-Context Inference","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2602.01405","title":"Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents","created":"2026-02-01","cited_by_count":4,"area":"agents"},{"id":"2602.12394","title":"Synthetic Interaction Data for Scalable Personalization in Large Language Models","created":"2026-02-12","cited_by_count":4,"area":null},{"id":"2603.23550","title":"Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction","created":"2026-03-21","cited_by_count":4,"area":null},{"id":"2603.25864","title":"GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2605.07937","title":"Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?","created":"2026-05-08","cited_by_count":4,"area":null},{"id":"2510.06800","title":"FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline","created":"2025-10-08","cited_by_count":3,"area":"agents"},{"id":"2510.25224","title":"ProMediate: A Socio-cognitive framework for evaluating proactive agents in multi-party negotiation","created":"2025-10-29","cited_by_count":3,"area":"agents"},{"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":"2602.15012","title":"Cold-Start Personalization via Training-Free Priors from Structured World Models","created":"2026-02-16","cited_by_count":3,"area":"wm"},{"id":"2602.19542","title":"Vinedresser3D: Agentic Text-guided 3D Editing","created":"2026-02-23","cited_by_count":3,"area":"agents"},{"id":"2603.25268","title":"CRAFT: Grounded Multi-Agent Coordination Under Partial Information","created":"2026-03-26","cited_by_count":3,"area":"agents"},{"id":"2604.07645","title":"PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent","created":"2026-04-08","cited_by_count":3,"area":"agents"},{"id":"2604.27093","title":"Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations","created":"2026-04-29","cited_by_count":3,"area":"alignment"},{"id":"2605.07305","title":"MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2605.24900","title":"ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents","created":"2026-05-24","cited_by_count":3,"area":"lr"},{"id":"2605.30251","title":"Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models","created":"2026-05-28","cited_by_count":3,"area":"distill"},{"id":"2608.12355","title":"Humans are Missing from AI Coding Agent Research","created":"2026-07-04","cited_by_count":3,"area":"agents"},{"id":"2505.01592","title":"AURA: A Diagnostic Framework for Tracking User Satisfaction of Interactive Planning Agents","created":"2025-05-02","cited_by_count":2,"area":"agents"},{"id":"2506.10157","title":"One Patient, Many Contexts: Scaling Medical AI with Contextual Intelligence","created":"2025-06-11","cited_by_count":2,"area":"mllm"},{"id":"2510.08872","title":"GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2601.09382","title":"Long-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments","created":"2026-01-14","cited_by_count":2,"area":"agents"},{"id":"2602.03468","title":"IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning","created":"2026-02-03","cited_by_count":2,"area":"lr"},{"id":"2602.11351","title":"Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization","created":"2026-02-11","cited_by_count":2,"area":"agents"},{"id":"2602.15259","title":"Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insight","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2602.22523","title":"Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents","created":"2026-02-26","cited_by_count":2,"area":"agents"},{"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":"2606.03698","title":"Multi$^2$: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2606.07818","title":"Representational Similarity and Model Behavior in Multi-Agent Interaction","created":"2026-06-05","cited_by_count":2,"area":"agents"},{"id":"2508.04563","title":"SID: Benchmarking Guided Instruction Capabilities in STEM Education with a Socratic Interdisciplinary Dialogues Dataset","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2508.05535","title":"Mixed-Initiative Dialog for Human-Robot Collaborative Manipulation","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2510.00777","title":"In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2510.06270","title":"MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learning","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2601.08403","title":"Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs","created":"2026-01-13","cited_by_count":1,"area":"lr"},{"id":"2601.17716","title":"Do Reasoning Models Ask Better Questions? A Formal Information-Theoretic Analysis on Multi-Turn LLM Games","created":"2026-01-25","cited_by_count":1,"area":"lr"},{"id":"2602.16488","title":"Learning to Learn from Language Feedback with Social Meta-Learning","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.13706","title":"Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models","created":"2026-04-15","cited_by_count":1,"area":"lr"},{"id":"2604.18398","title":"AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.23815","title":"DRACULA: Hunting for the Actions Users Want Deep Research Agents to Execute","created":"2026-04-26","cited_by_count":1,"area":"agents"},{"id":"2605.15205","title":"Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2605.29392","title":"Offloading Score: Measuring AI Reliance Through Counterfactual Workflows","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2607.10428","title":"Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2607.14240","title":"Align AI to Dynamic Human-AI Workflows","created":"2026-07-15","cited_by_count":1,"area":"alignment"},{"id":"2607.16352","title":"Clarify Before Executing: A Self-Evolving Agent for Resolving Intent Asymmetry in 3D Tool Orchestration","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2607.16412","title":"Interactive Task Alignment as a POMDP","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2608.17150","title":"KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2608.27818","title":"AcCoRD: Evaluating User-Agent Collaboration Under Realistic User Preference Dynamics","created":"2026-08-28","cited_by_count":1,"area":"agents"},{"id":"2609.15972","title":"Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2609.21117","title":"From Task Success to Productive Success: Evaluating Human-AI Collaboration by Quality and Cost","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2601.08653","title":"Prism: Towards Lowering User Cognitive Load in LLMs via Complex Intent Understanding","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2602.15854","title":"Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization","created":"2026-01-24","cited_by_count":0,"area":"alignment"},{"id":"2603.16944","title":"Omni IIE Bench: Benchmarking the Practical Capabilities of Image Editing Models","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.17094","title":"Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.00414","title":"Decision-Centric Design for LLM Systems","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.02315","title":"Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.21827","title":"Alignment has a Fantasia Problem","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.25204","title":"Clarification Is Not Enough: Post-Clarification Answering Remains the Bottleneck in Multi-Turn QA","created":"2026-05-24","cited_by_count":0,"area":null},{"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":"2605.26969","title":"Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2606.00728","title":"From Empathy to Personalized Empathy: Adapting Empathetic Strategies to Individual Users","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.01182","title":"CA-BED: Conversation-Aware Bayesian Experimental Design","created":"2026-05-31","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}