{"total":54,"rows":[{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145,"area":"lr"},{"id":"2503.22674","title":"QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?","created":"2025-03-28","cited_by_count":63,"area":"lr"},{"id":"2502.13069","title":"Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering","created":"2025-02-18","cited_by_count":38,"area":"agents"},{"id":"2505.13360","title":"What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts","created":"2025-05-19","cited_by_count":32,"area":null},{"id":"2505.22655","title":"Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents","created":"2025-05-28","cited_by_count":32,"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":"2602.11348","title":"AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition","created":"2026-02-11","cited_by_count":23,"area":"agents"},{"id":"2502.21239","title":"Semantic Volume: Quantifying and Detecting both External and Internal Uncertainty in LLMs","created":"2025-02-28","cited_by_count":20,"area":null},{"id":"2607.10059","title":"AgentAbstain: Do LLM Agents Know When Not to Act?","created":"2026-07-11","cited_by_count":17,"area":"agents"},{"id":"2606.28733","title":"Agentic Abstention: Do Agents Know When to Stop Instead of Act?","created":"2026-06-27","cited_by_count":15,"area":"agents"},{"id":"2509.13813","title":"Geometric Uncertainty for Detecting and Correcting Hallucinations in LLMs","created":"2025-09-17","cited_by_count":13,"area":null},{"id":"2406.12307","title":"Can Tool-augmented Large Language Models be Aware of Incomplete Conditions?","created":"2024-06-18","cited_by_count":8,"area":"agents"},{"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":"2505.17455","title":"Towards Evaluating Proactive Risk Awareness of Multimodal Language Models","created":"2025-05-23","cited_by_count":6,"area":"mllm"},{"id":"2605.27209","title":"Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments","created":"2026-05-26","cited_by_count":6,"area":"agents"},{"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":"2503.00179","title":"Zero-Shot and Efficient Clarification Need Prediction in Conversational Search","created":"2025-02-28","cited_by_count":4,"area":null},{"id":"2505.14549","title":"Can Large Language Models Really Recognize Your Name?","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2508.06056","title":"RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation","created":"2025-08-08","cited_by_count":4,"area":"rag"},{"id":"2602.20042","title":"AI Alignment Breaks at the Edge","created":"2026-02-23","cited_by_count":4,"area":"alignment"},{"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":"2605.20544","title":"The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents","created":"2026-05-19","cited_by_count":4,"area":"mllm"},{"id":"2504.09665","title":"CLEAR-KGQA: Clarification-Enhanced Ambiguity Resolution for Knowledge Graph Question Answering","created":"2025-04-13","cited_by_count":3,"area":null},{"id":"2510.13835","title":"ConDABench: Interactive Evaluation of Language Models for Data Analysis","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2603.05801","title":"Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks","created":"2026-03-06","cited_by_count":3,"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":"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":"2608.19564","title":"Remember, Verify, or Ask? Cross-Family Evaluation of Memory Commitment in LLM Agents","created":"2026-08-20","cited_by_count":2,"area":"agents"},{"id":"2505.11533","title":"A Data Synthesis Method Driven by Large Language Models for Proactive Mining of Implicit User Intentions in Tourism","created":"2025-05-14","cited_by_count":1,"area":"synth"},{"id":"2505.23410","title":"From Parameters to Prompts: Understanding and Mitigating the Factuality Gap between Fine-Tuned LLMs","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2601.23281","title":"User Prompting Strategies and Prompt Enhancement Methods for Open-Set Object Detection in XR Environments","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.02843","title":"Act or Clarify? Modeling Sensitivity to Uncertainty and Cost in Communication","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.03970","title":"Generative AI for Managerial Decision-Making under Ambiguity and Sycophancy","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2608.20220","title":"InsufficiencyBench: Evaluating LLM legal advice on underspecified user queries","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2407.12017","title":"Follow-Up Questions Improve Documents Generated by Large Language Models","created":"2024-06-27","cited_by_count":0,"area":null},{"id":"2606.01581","title":"Agent System Operations: Categorization, Challenges, and Future Directions","created":"2026-06-01","cited_by_count":0,"area":"lr"},{"id":"2606.23590","title":"TIPS: Topological Ill-Posedness Probing and Steering in Large Language Models","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.14105","title":"Automatically Evolving Prompt Guidelines for Task-Specific Optimization","created":"2026-05-07","cited_by_count":0,"area":null},{"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":"2607.17341","title":"Understanding From Human Perspective: A Multi-agent System for Interactive Egocentric Medical Image Segmentation","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2608.00018","title":"CITBench: A Comprehensive Benchmark for Interactive Tabular Data Processing with LLMs","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.02372","title":"PredAct-Bench: Benchmarking Tool-Augmented Dialogue under Controlled Tool Noise","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.19202","title":"Active Inference as Context Acquisition for AI Agents","created":"2026-06-08","cited_by_count":0,"area":"agents"},{"id":"2608.19875","title":"A knowledge-guided agentic framework for mitigating patient-context ambiguity in health queries","created":"2026-08-20","cited_by_count":0,"area":"agents"},{"id":"2608.25325","title":"FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk Review","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.07395","title":"Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.35879","title":"CruxBench: A Benchmark of Information Discovery","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.37267","title":"Foundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.05532","title":"DelegationBench: Measuring When AI Agents Should Ask Before Acting","created":"2026-10-04","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":"2610.14539","title":"FDE-Bench: Evaluating End-to-End Delivery from Underspecified Real-World Business Requests","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.18090","title":"AM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.20052","title":"What Is a Clarification? Estimating Model-Dependent Input Ambiguity","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20195","title":"What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}