{"total":79,"rows":[{"id":"2310.02170","title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","created":"2023-10-03","cited_by_count":290,"area":"agents"},{"id":"2503.03750","title":"The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems","created":"2025-03-05","cited_by_count":72,"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":"2405.14751","title":"AGILE: A Novel Reinforcement Learning Framework of LLM Agents","created":"2024-05-23","cited_by_count":45,"area":"agents"},{"id":"2412.04141","title":"Reducing Tool Hallucination via Reliability Alignment","created":"2024-12-05","cited_by_count":39,"area":"agents"},{"id":"2404.09127","title":"Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation","created":"2024-04-14","cited_by_count":26,"area":"agents"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2509.14034","title":"Enhancing Multi-Agent Debate System Performance via Confidence Expression","created":"2025-09-17","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":"2406.00252","title":"Towards Rationality in Language and Multimodal Agents: A Survey","created":"2024-06-01","cited_by_count":16,"area":"agents"},{"id":"2601.07264","title":"The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents","created":"2026-01-12","cited_by_count":16,"area":"agents"},{"id":"2602.02905","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","created":"2026-02-02","cited_by_count":16,"area":"agents"},{"id":"2407.06426","title":"DebUnc: Improving Large Language Model Agent Communication With Uncertainty Metrics","created":"2024-07-08","cited_by_count":14,"area":"agents"},{"id":"2503.12651","title":"VeriLA: A Human-Centered Evaluation Framework for Interpretable Verification of LLM Agent Failures","created":"2025-03-16","cited_by_count":14,"area":"agents"},{"id":"2412.12151","title":"SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration","created":"2024-12-11","cited_by_count":13,"area":"agents"},{"id":"2502.15865","title":"Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk","created":"2025-02-21","cited_by_count":13,"area":"agents"},{"id":"2508.07935","title":"SHIELDA: Structured Handling of Exceptions in LLM-Driven Agentic Workflows","created":"2025-08-11","cited_by_count":13,"area":"agents"},{"id":"2606.00198","title":"BAGEN: Are LLM Agents Budget-Aware?","created":"2026-05-29","cited_by_count":13,"area":"agents"},{"id":"2412.13667","title":"Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery","created":"2024-12-18","cited_by_count":11,"area":"agents"},{"id":"2605.11436","title":"Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty","created":"2026-05-12","cited_by_count":10,"area":"agents"},{"id":"2605.20251","title":"ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents","created":"2026-05-18","cited_by_count":6,"area":"agents"},{"id":"2608.00316","title":"Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch","created":"2026-07-31","cited_by_count":6,"area":"agents"},{"id":"2511.13240","title":"Knowing What You Know Is Not Enough: Large Language Model Confidences Don't Align With Their Actions","created":"2025-11-17","cited_by_count":4,"area":"agents"},{"id":"2603.20975","title":"DiscoUQ: Structured Disagreement Analysis for Uncertainty Quantification in LLM Agent Ensembles","created":"2026-03-21","cited_by_count":4,"area":"agents"},{"id":"2605.09278","title":"EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium","created":"2026-05-10","cited_by_count":4,"area":"agents"},{"id":"2502.15690","title":"Level-Navi Agent: A Framework and benchmark for Chinese Web Search Agents","created":"2024-12-20","cited_by_count":3,"area":"agents"},{"id":"2601.10865","title":"Multi-Agent Taint Specification Extraction for Vulnerability Detection","created":"2026-01-15","cited_by_count":3,"area":"agents"},{"id":"2602.11619","title":"When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents","created":"2026-02-12","cited_by_count":3,"area":"agents"},{"id":"2603.02960","title":"Architecting Trust in Artificial Epistemic Agents","created":"2026-03-03","cited_by_count":3,"area":"agents"},{"id":"2604.12262","title":"CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades","created":"2026-04-14","cited_by_count":3,"area":"agents"},{"id":"2606.14211","title":"Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL","created":"2026-06-12","cited_by_count":3,"area":"agents"},{"id":"2608.26846","title":"Evaluating Confidence-Gated Retrieval with Matched Trajectory Replay","created":"2026-08-27","cited_by_count":3,"area":"agents"},{"id":"2312.17601","title":"The Tyranny of Possibilities in the Design of Task-Oriented LLM Systems: A Scoping Survey","created":"2023-12-29","cited_by_count":2,"area":"agents"},{"id":"2508.19096","title":"Trustworthy Agents for Electronic Health Records through Confidence Estimation","created":"2025-08-26","cited_by_count":2,"area":"agents"},{"id":"2510.02185","title":"FalseCrashReducer: Mitigating False Positive Crashes in OSS-Fuzz-Gen Using Agentic AI","created":"2025-10-02","cited_by_count":2,"area":"agents"},{"id":"2605.17292","title":"MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"id":"2607.12397","title":"Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents","created":"2026-07-14","cited_by_count":2,"area":"agents"},{"id":"2609.00038","title":"trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories","created":"2026-08-29","cited_by_count":2,"area":"agents"},{"id":"2502.01691","title":"Agent-Based Uncertainty Awareness Improves Automated Radiology Report Labeling with an Open-Source Large Language Model","created":"2025-02-02","cited_by_count":1,"area":"agents"},{"id":"2604.05952","title":"Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration","created":"2026-04-07","cited_by_count":1,"area":"agents"},{"id":"2605.21781","title":"Reflective Prompt Tuning through Language Model Function-Calling","created":"2026-05-20","cited_by_count":1,"area":"agents"},{"id":"2605.22949","title":"MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination","created":"2026-05-21","cited_by_count":1,"area":"agents"},{"id":"2606.08348","title":"Bayesian-Agent: Posterior-Guided Skill Evolution Across LLM Agent Harnesses","created":"2026-06-06","cited_by_count":1,"area":"agents"},{"id":"2608.11552","title":"Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents","created":"2026-08-12","cited_by_count":1,"area":"agents"},{"id":"2608.16002","title":"From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents","created":"2026-08-17","cited_by_count":1,"area":"agents"},{"id":"2608.23058","title":"LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications","created":"2026-08-24","cited_by_count":1,"area":"agents"},{"id":"2609.18998","title":"One Axis, No Brake: Self-Knowledge Limits the Filtering of Harmful Peer Conformity in LLMs","created":"2026-07-17","cited_by_count":1,"area":"agents"},{"id":"2609.20211","title":"Silence Is Endorsement: Verification-Status Laundering in LLM Agent Pipelines","created":"2026-07-25","cited_by_count":1,"area":"agents"},{"id":"2610.05107","title":"SearchJev: A Fast and Calibrated System-1 Model for Search Agents","created":"2026-10-04","cited_by_count":1,"area":"agents"},{"id":"2504.18839","title":"Detect, Explain, Escalate: Sustainable Dialogue Breakdown Management for LLM Agents","created":"2025-04-26","cited_by_count":0,"area":"agents"},{"id":"2509.08809","title":"Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals","created":"2025-09-10","cited_by_count":0,"area":"agents"},{"id":"2512.00617","title":"ART: Adaptive Response Tuning Framework -- A Multi-Agent Tournament-Based Approach to LLM Response Optimization","created":"2025-11-29","cited_by_count":0,"area":"agents"},{"id":"2604.16752","title":"Don't Start What You Can't Finish: A Counterfactual Audit of Support-State Triage in LLM Agents","created":"2026-04-17","cited_by_count":0,"area":"agents"},{"id":"2605.06028","title":"Multi-agent decision making: A Blackwell's informativeness approach","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2606.01584","title":"Identifying High-Confidence Social Biases in LLMs for Trustworthy Conversational Tutoring Agents","created":"2026-06-01","cited_by_count":0,"area":"agents"},{"id":"2606.03812","title":"Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2606.11349","title":"Knowing When to Ask: Self-Gated Clarification for Hierarchical Language Agents","created":"2026-06-09","cited_by_count":0,"area":"agents"},{"id":"2606.13749","title":"Large Language Models as Supervised Extraction Assistants: Lowering the Barrier to Documentation Standard Adoption in Agent-Based Modelling","created":"2026-06-11","cited_by_count":0,"area":"agents"},{"id":"2606.17203","title":"Trust-Aware Multi-Agent Traceability: Confidence-Calibrated Knowledge Graphs for Consistent Software Artifact Management","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2606.19356","title":"Trustworthy Multi-Agent Systems: Mitigating Semantic Drift with the Argent Signaling Protocol","created":"2026-05-14","cited_by_count":0,"area":"agents"},{"id":"2607.14108","title":"Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2607.28317","title":"One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2608.10330","title":"Hierarchical Compositionality for An Assistive AI Agent","created":"2026-08-11","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":"2608.22130","title":"PropUQ-MAS: Propagation-Aware Uncertainty Quantification for LLM Multi-Agent Systems","created":"2026-08-22","cited_by_count":0,"area":"agents"},{"id":"2609.00652","title":"Self-Reports Are Not Verification: Environment-Grounded Auditing of LLM Operators in Evolutionary Search","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.00935","title":"DualStake: Dual-Path Confidence Calibration in Deep Research Agents","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"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":"2609.08016","title":"What Does Multi-Agent LLM Debate Actually Change? A Layered Analysis of Disagreement and Answer Quality","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.13261","title":"From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaboration","created":"2026-09-06","cited_by_count":0,"area":"agents"},{"id":"2609.24277","title":"How Many Pixels Is a Digit Worth? Place-Aware Coordinate Entropy for GUI Agent Confidence Estimation","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2609.32081","title":"Toward Interactive Understanding of Code APIs","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.40103","title":"JuryFlow: Disagreement-Guided Human-in-the-Loop Multi-Agent Evaluation","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.03894","title":"Proxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-Probabilities","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04156","title":"Trajectory-Derived Confidence for Reliable, Resource-Aware Clinical Text-to-SQL Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.07570","title":"Unanimously Wrong: Certified Abstention from How Medical LLM Consensus Forms","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.09115","title":"From Uncertainty to Action: Learning to Steer LLM Agents","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.18614","title":"Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.19226","title":"Agentic Self-Awareness: Aligning Knowing, Acting, and Holding","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}