{"total":76,"rows":[{"id":"2507.22034","title":"UserBench: An Interactive Gym Environment for User-Centric Agents","created":"2025-07-29","cited_by_count":76,"area":"agents"},{"id":"2509.18970","title":"LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions","created":"2025-09-23","cited_by_count":50,"area":"agents"},{"id":"2511.08798","title":"Structured Uncertainty guided Clarification for LLM Agents","created":"2025-11-11","cited_by_count":41,"area":"agents"},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2604.09408","title":"HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?","created":"2026-04-10","cited_by_count":27,"area":"agents"},{"id":"2502.14860","title":"ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning","created":"2025-02-20","cited_by_count":25,"area":"lr"},{"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":"2507.23158","title":"User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signal","created":"2025-07-30","cited_by_count":19,"area":null},{"id":"2603.26233","title":"Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents","created":"2026-03-27","cited_by_count":19,"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":"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":"2502.18448","title":"Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing","created":"2025-02-25","cited_by_count":13,"area":null},{"id":"2411.07237","title":"Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries","created":"2024-11-11","cited_by_count":12,"area":null},{"id":"2509.16330","title":"Generalizability of Large Language Model-Based Agents: A Comprehensive Survey","created":"2025-09-19","cited_by_count":10,"area":"agents"},{"id":"2510.07593","title":"AgentAsk: Multi-Agent Systems Need to Ask","created":"2025-10-08","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":"2510.08517","title":"CaRT: Teaching LLM Agents to Know When They Know Enough","created":"2025-10-09","cited_by_count":7,"area":"agents"},{"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":"2602.03664","title":"Mitigating Conversational Inertia in Multi-Turn Agents","created":"2026-02-03","cited_by_count":7,"area":"agents"},{"id":"2505.12543","title":"Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey","created":"2025-05-18","cited_by_count":6,"area":"agents"},{"id":"2602.03429","title":"DiscoverLLM: From Executing Intents to Discovering Them","created":"2026-02-03","cited_by_count":6,"area":null},{"id":"2506.09173","title":"The Curious Language Model: Strategic Test-Time Information Acquisition","created":"2025-06-10","cited_by_count":5,"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":"2605.09698","title":"Ambig-DS: A Benchmark for Task-Framing Ambiguity in Data-Science Agents","created":"2026-05-10","cited_by_count":5,"area":"agents"},{"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":"2603.12011","title":"Can RL Improve Generalization of LLM Agents? An Empirical Study","created":"2026-03-12","cited_by_count":4,"area":"agents"},{"id":"2604.14624","title":"Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks","created":"2026-04-16","cited_by_count":4,"area":null},{"id":"2606.01912","title":"SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart Homes","created":"2026-06-01","cited_by_count":4,"area":"lr"},{"id":"2601.16400","title":"Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification","created":"2026-01-23","cited_by_count":3,"area":"agents"},{"id":"2603.05909","title":"InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2603.29373","title":"Beyond Idealized Patients: Evaluating LLMs under Challenging Patient Behaviors in Medical Consultations","created":"2026-03-31","cited_by_count":3,"area":null},{"id":"2604.02666","title":"Let's Have a Conversation: Designing and Evaluating LLM Agents for Interactive Optimization","created":"2026-04-03","cited_by_count":3,"area":"agents"},{"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":"2504.11277","title":"From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMs","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2506.20876","title":"Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2508.08308","title":"First Ask Then Answer: A Framework Design for AI Dialogue Based on Supplementary Questioning with Large Language Models","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2603.16120","title":"Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2604.19656","title":"Pause or Fabricate? Training Language Models for Grounded Reasoning","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2605.16462","title":"Asking Back: Interaction-Layer Antidistillation Watermarks","created":"2026-05-15","cited_by_count":2,"area":"distill"},{"id":"2605.18630","title":"SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2609.03727","title":"Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation","created":"2026-09-03","cited_by_count":2,"area":"agents"},{"id":"2507.12370","title":"Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2509.22750","title":"MARCH: Evaluating the Intersection of Ambiguity Interpretation and Multi-hop Inference","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"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":"2602.16488","title":"Learning to Learn from Language Feedback with Social Meta-Learning","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2605.25831","title":"Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2606.12587","title":"Strategic Decision Support for AI Agents","created":"2026-06-10","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":"2508.07279","title":"MAQuA: Adaptive Question-Asking for Multidimensional Mental Health Screening using Item Response Theory","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2510.27410","title":"Closing the Expression Gap in LLM Instructions via Socratic Questioning","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2512.13154","title":"MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2601.16508","title":"Is Length Really A Liability? An Evaluation of Multi-turn LLM Conversations using BoolQ","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2604.02382","title":"Interactive Clarification for Cloud Infrastructure-as-Code Synthesis","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.03924","title":"Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2604.15140","title":"DiscoTrace: Representing and Comparing Answering Strategies of Humans and LLMs in Information-Seeking Question Answering","created":"2026-04-16","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":"2605.11240","title":"When to Ask a Question: Understanding Communication Strategies in Generative AI Tools","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.24266","title":"An Interactive Paradigm for Deep Research","created":"2026-05-22","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":"2606.01182","title":"CA-BED: Conversation-Aware Bayesian Experimental Design","created":"2026-05-31","cited_by_count":0,"area":"lr"},{"id":"2606.07629","title":"Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences","created":"2026-05-30","cited_by_count":0,"area":"alignment"},{"id":"2607.14250","title":"The Severance Problem: LLMs are Unaware of the Person Beyond the Prompt","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.26611","title":"Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.11631","title":"CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurement","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.30738","title":"Not All Fallbacks Are Failures: Understanding and Recovering from Fallbacks in Mobile Voice Assistants","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.05258","title":"Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.23939","title":"XYEval: Agents say yes to bad advice","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.24290","title":"When and How Should an Agent Clarify? CIGAsk: Teaching LLMs to Clarify via Counterfactual Information Gain","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.33017","title":"Trust and Task Completion in the World of Consumer AI Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.37236","title":"Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01769","title":"CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.04719","title":"Learning to Clarify Underspecified Intents Under Limited Interaction","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.12655","title":"CLEAT: Learning Value-Guided Clarification for Interactive Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.15154","title":"Where Did We Go Wrong? Localizing Errors to Repair Multi-Turn Conversations","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.20052","title":"What Is a Clarification? Estimating Model-Dependent Input Ambiguity","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}