{"total":56,"rows":[{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2412.18174","title":"INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent","created":"2024-12-24","cited_by_count":64,"area":"agents"},{"id":"2501.09781","title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos","created":"2025-01-16","cited_by_count":43,"area":null},{"id":"2410.15413","title":"A Comprehensive Evaluation of Cognitive Biases in LLMs","created":"2024-10-20","cited_by_count":34,"area":null},{"id":"2405.01745","title":"Large Language Models for UAVs: Current State and Pathways to the Future","created":"2024-05-02","cited_by_count":33,"area":null},{"id":"2511.11562","title":"PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning","created":"2025-11-14","cited_by_count":32,"area":null},{"id":"2407.19098","title":"Evaluating Human-AI Collaboration: A Review and Methodological Framework","created":"2024-07-09","cited_by_count":27,"area":null},{"id":"2407.13934","title":"Towards Trustworthy AI: A Review of Ethical and Robust Large Language Models","created":"2024-06-01","cited_by_count":22,"area":null},{"id":"2406.11096","title":"The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models","created":"2024-06-16","cited_by_count":19,"area":null},{"id":"2510.25779","title":"Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets","created":"2025-10-27","cited_by_count":19,"area":"agents"},{"id":"2502.11098","title":"Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems","created":"2025-02-16","cited_by_count":17,"area":"agents"},{"id":"2403.06294","title":"ArgMed-Agents: Explainable Clinical Decision Reasoning with LLM Disscusion via Argumentation Schemes","created":"2024-03-10","cited_by_count":13,"area":"lr"},{"id":"2407.11282","title":"Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models","created":"2024-07-15","cited_by_count":13,"area":"safety"},{"id":"2411.14491","title":"A Survey on Human-Centric LLMs","created":"2024-11-20","cited_by_count":13,"area":null},{"id":"2407.03000","title":"VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values","created":"2024-07-03","cited_by_count":12,"area":"mllm"},{"id":"2504.06771","title":"AI, Help Me Think$\\unicode{x2014}$but for Myself: Assisting People in Complex Decision-Making by Providing Different Kinds of Cognitive Support","created":"2025-04-09","cited_by_count":12,"area":"lr"},{"id":"2505.21397","title":"DecisionFlow: Advancing Large Language Model as Principled Decision Maker","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2503.18419","title":"Generative AI in Knowledge Work: Design Implications for Data Navigation and Decision-Making","created":"2025-03-24","cited_by_count":9,"area":null},{"id":"2512.11437","title":"CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare","created":"2025-12-12","cited_by_count":9,"area":null},{"id":"2503.09223","title":"LREF: A Novel LLM-based Relevance Framework for E-commerce","created":"2025-03-12","cited_by_count":8,"area":null},{"id":"2503.09326","title":"A Survey on Enhancing Causal Reasoning Ability of Large Language Models","created":"2025-03-12","cited_by_count":8,"area":"lr"},{"id":"2410.12583","title":"STRUX: An LLM for Decision-Making with Structured Explanations","created":"2024-10-16","cited_by_count":7,"area":null},{"id":"2501.06695","title":"DVM: Towards Controllable LLM Agents in Social Deduction Games","created":"2025-01-12","cited_by_count":7,"area":"agents"},{"id":"2507.01378","title":"RALLY: Role-Adaptive LLM-Driven Yoked Navigation for Agentic UAV Swarms","created":"2025-07-02","cited_by_count":7,"area":"agents"},{"id":"2412.05187","title":"SurgBox: Agent-Driven Operating Room Sandbox with Surgery Copilot","created":"2024-12-06","cited_by_count":6,"area":"agents"},{"id":"2502.12149","title":"HARBOR: Exploring Persona Dynamics in Multi-Agent Competition","created":"2025-02-17","cited_by_count":6,"area":"agents"},{"id":"2512.23511","title":"Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Proving","created":"2025-12-29","cited_by_count":6,"area":"lr"},{"id":"2412.02904","title":"Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning","created":"2024-12-03","cited_by_count":5,"area":null},{"id":"2504.19445","title":"Systematic Bias in Large Language Models: Discrepant Response Patterns in Binary vs. Continuous Judgment Tasks","created":"2025-04-28","cited_by_count":5,"area":null},{"id":"2510.08962","title":"Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation","created":"2025-10-10","cited_by_count":5,"area":null},{"id":"2512.07890","title":"CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models","created":"2025-12-02","cited_by_count":5,"area":null},{"id":"2604.27914","title":"Geometry-Calibrated Conformal Abstention for Language Models","created":"2026-04-30","cited_by_count":5,"area":null},{"id":"2403.16501","title":"Learning To Guide Human Decision Makers With Vision-Language Models","created":"2024-03-25","cited_by_count":4,"area":null},{"id":"2407.05977","title":"Exploring Human-LLM Conversations: Mental Models and the Originator of Toxicity","created":"2024-07-08","cited_by_count":4,"area":null},{"id":"2410.01772","title":"DeFine: Decision-Making with Analogical Reasoning over Factor Profiles","created":"2024-10-02","cited_by_count":4,"area":"lr"},{"id":"2507.15676","title":"Agentic AI for autonomous anomaly management in complex systems","created":"2025-07-21","cited_by_count":4,"area":"agents"},{"id":"2407.02885","title":"CogErgLLM: Exploring Large Language Model Systems Design Perspective Using Cognitive Ergonomics","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2507.08440","title":"Finding Common Ground: Using Large Language Models to Detect Agreement in Multi-Agent Decision Conferences","created":"2025-07-11","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":"2510.27251","title":"FinPos: A Position-Aware Trading Agent System for Real Financial Markets","created":"2025-10-31","cited_by_count":3,"area":"agents"},{"id":"2601.13284","title":"Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2504.15801","title":"A closer look at how large language models trust humans: patterns and biases","created":"2025-04-22","cited_by_count":2,"area":"agents"},{"id":"2410.02231","title":"SEAL: SEmantic-Augmented Imitation Learning via Language Model","created":"2024-10-03","cited_by_count":1,"area":"offlinerl"},{"id":"2505.15596","title":"Exploring LLM-Generated Feedback for Economics Essays: How Teaching Assistants Evaluate and Envision Its Use","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2506.20018","title":"Achieving Trustworthy Real-Time Decision Support Systems with Low-Latency Interpretable AI Models","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2608.26291","title":"Assessing mentalization in humans and large language models","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2509.09735","title":"Discrimination by LLMs: Cross-lingual Bias Assessment and Mitigation in Decision-Making and Summarisation","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2601.11286","title":"XChoice: Explainable Evaluation of AI-Human Alignment in LLM-based Constrained Choice Decision Making","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2602.22070","title":"Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts","created":"2026-02-25","cited_by_count":0,"area":"agents"},{"id":"2604.09029","title":"CONDESION-BENCH: Conditional Decision-Making of Large Language Models in Compositional Action Space","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2604.18122","title":"Decisive: Guiding User Decisions with Optimal Preference Elicitation from Unstructured Documents","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.24348","title":"OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents","created":"2026-04-27","cited_by_count":0,"area":"mllm"},{"id":"2606.08323","title":"\"So There's a Catch-22 Here\": How Early Adopters Who Build Multi-Agent LLM Systems Conceptualize Transparency","created":"2026-06-06","cited_by_count":0,"area":"agents"},{"id":"2606.20227","title":"QMFOL: Benchmarking Large Language Model Reasoning via Quantifiable Monadic First-Order Logic Test Case Generation","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2607.01242","title":"ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2610.19138","title":"MA-Bench: Measuring Operational Planning in Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}