{"total":106,"rows":[{"id":"2603.11245","title":"Mind the Sim2Real Gap in User Simulation for Agentic Tasks","created":"2026-03-11","cited_by_count":54,"area":"agents"},{"id":"2601.17087","title":"Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluations","created":"2026-01-23","cited_by_count":40,"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":"2410.02551","title":"ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration","created":"2024-10-03","cited_by_count":23,"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":"2601.15703","title":"Agentic Uncertainty Quantification","created":"2026-01-22","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":"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":"2504.20168","title":"MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools","created":"2025-04-28","cited_by_count":15,"area":"agents"},{"id":"2601.15778","title":"Agentic Confidence Calibration","created":"2026-01-22","cited_by_count":15,"area":"agents"},{"id":"2602.03338","title":"Accurate Failure Prediction in Agents Does Not Imply Effective Failure Prevention","created":"2026-02-03","cited_by_count":15,"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":"2407.11843","title":"Preemptive Detection and Correction of Misaligned Actions in LLM Agents","created":"2024-07-16","cited_by_count":10,"area":"agents"},{"id":"2606.22936","title":"When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents","created":"2026-06-22","cited_by_count":10,"area":"agents"},{"id":"2602.11541","title":"Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use","created":"2026-02-12","cited_by_count":8,"area":"agents"},{"id":"2605.30653","title":"Counterfactual Graph for Multi-Agent LLM Calibration","created":"2026-05-28","cited_by_count":7,"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":"2603.02798","title":"Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification","created":"2026-03-03","cited_by_count":5,"area":"agents"},{"id":"2608.02464","title":"Real-Time Detection and Repair of LLM Agent Failures","created":"2026-08-03","cited_by_count":5,"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":"2605.27955","title":"Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents","created":"2026-05-27","cited_by_count":4,"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":"2603.23115","title":"AgentFoX: LLM Agent-Guided Fusion with eXplainability for AI-Generated Image Detection","created":"2026-03-24","cited_by_count":3,"area":"agents"},{"id":"2605.16895","title":"The Alpha Illusion: Reported Alpha from LLM Trading Agents Should Not Be Treated as Deployment Evidence","created":"2026-05-16","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":"2502.11312","title":"AI Generations: From AI 1.0 to AI 4.0","created":"2025-02-16","cited_by_count":2,"area":"agents"},{"id":"2603.27299","title":"From Inference Routing to Agent Orchestration: Declarative Policy Compilation with Cross-Layer Verification","created":"2026-03-28","cited_by_count":2,"area":"agents"},{"id":"2604.04269","title":"Beyond Fluency: Toward Reliable Trajectories in Agentic IR","created":"2026-04-05","cited_by_count":2,"area":"agents"},{"id":"2604.05116","title":"Uncertainty-Guided Latent Diagnostic Trajectory Learning for Sequential Clinical Diagnosis","created":"2026-04-06","cited_by_count":2,"area":"agents"},{"id":"2604.09791","title":"Pioneer Agent: Continual Improvement of Small Language Models in Production","created":"2026-04-10","cited_by_count":2,"area":"agents"},{"id":"2604.26733","title":"FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards","created":"2026-04-29","cited_by_count":2,"area":"agents"},{"id":"2605.12729","title":"Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety","created":"2026-05-12","cited_by_count":2,"area":"agents"},{"id":"2605.16604","title":"R2V Agent: Teaching SLMs When to Ask for Help","created":"2026-05-15","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":"2606.01828","title":"Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus","created":"2026-06-01","cited_by_count":2,"area":"agents"},{"id":"2607.10645","title":"MafiaScope: Non-Invasive, Time-Resolved Belief Probing for LLM Agents in Social Deduction Games","created":"2026-07-12","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":"2609.00949","title":"Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling","created":"2026-09-01","cited_by_count":2,"area":"agents"},{"id":"2609.26863","title":"SkillApt: Learning When to Activate Agent Skills from Counterfactual Evidence","created":"2026-09-22","cited_by_count":2,"area":"agents"},{"id":"2610.02267","title":"Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses","created":"2026-10-01","cited_by_count":2,"area":"agents"},{"id":"2403.17860","title":"Illuminating Blind Spots of Language Models with Targeted Agent-in-the-Loop Synthetic Data","created":"2024-03-26","cited_by_count":1,"area":"agents"},{"id":"2602.12083","title":"Differentiable Modal Logic for Multi-Agent Diagnosis, Orchestration and Communication","created":"2026-02-12","cited_by_count":1,"area":"agents"},{"id":"2604.04220","title":"TimeSeek: Temporal Reliability of Agentic Forecasters","created":"2026-04-05","cited_by_count":1,"area":"agents"},{"id":"2604.19752","title":"Soft-Label Governance for Distributional Safety in Multi-Agent Systems","created":"2026-03-19","cited_by_count":1,"area":"agents"},{"id":"2605.03838","title":"TRACE: A Metrologically-Grounded Engineering Framework for Trustworthy Agentic AI Systems in Operationally Critical Domains","created":"2026-05-05","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":"2606.31371","title":"Calibrating the Evaluator: Does Probability Calibration Mitigate Preference Coupling in LLM Agent Feedback Loops?","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2607.04528","title":"Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents","created":"2026-07-05","cited_by_count":1,"area":"agents"},{"id":"2607.09521","title":"SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction","created":"2026-07-10","cited_by_count":1,"area":"agents"},{"id":"2607.17765","title":"FIFA World Cup 2026 as a Contamination-Free Benchmark for LLM Forecasting Agents: Four Models, a Bookmaker, and 104 Matches","created":"2026-07-20","cited_by_count":1,"area":"agents"},{"id":"2608.05199","title":"Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2608.09254","title":"Business Truth, not SQL Accuracy: A Rule-Gated 7B Analytics Agent Outperforms a Direct-Prompted 32B Baseline","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2609.05274","title":"How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2609.25647","title":"Testing-Driven Reliability Audit of Trajectory-Based Early Outcome Prediction for LLM Agents: Target-Specific Calibration Transfer Persists Within a Single Benchmark","created":"2026-09-22","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":"2510.01654","title":"SoK: Measuring What Matters for Closed-Loop Security Agents","created":"2025-10-02","cited_by_count":0,"area":"agents"},{"id":"2512.04988","title":"When AI Agents Compete for Jobs: Strategic Capabilities and Economic Dynamics of AI Labour Markets","created":"2025-12-04","cited_by_count":0,"area":"agents"},{"id":"2602.14251","title":"Multi-Agent Debate: A Unified Agentic Framework for Tabular Anomaly Detection","created":"2026-02-15","cited_by_count":0,"area":"agents"},{"id":"2602.18922","title":"Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot Learning","created":"2026-02-21","cited_by_count":0,"area":"agents"},{"id":"2602.22442","title":"A Framework for Assessing AI Agent Decisions and Outcomes in AutoML Pipelines","created":"2026-02-25","cited_by_count":0,"area":"agents"},{"id":"2604.12513","title":"Agentic Control in Variational Language Models","created":"2026-04-14","cited_by_count":0,"area":"agents"},{"id":"2605.01847","title":"NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles","created":"2026-05-03","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":"2605.09534","title":"Governing AI-Assisted Security Operations: A Design Science Framework for Operational Decision Support","created":"2026-05-10","cited_by_count":0,"area":"agents"},{"id":"2605.30858","title":"ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2606.10304","title":"MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents","created":"2026-06-09","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":"2606.17203","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":"2607.00297","title":"EPC: A Standardized Protocol for Measuring Evaluator Preference Dynamics in LLM Agent Systems","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2607.09623","title":"Task-Specific Multimodal Question Answering Agents via Confidence Calibration and Incremental Reasoning for QANTA 2026","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2607.09762","title":"BatteryLake: Agentic, Physics-Grounded Curation of Heterogeneous Battery Aging Data and Benchmarking","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2607.13411","title":"Evaluating Frontier AI Agents as Autonomous Clinical Security Auditors","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2607.16229","title":"FinBench: Time-Gated Calibration and Uncertainty Benchmarking for Agentic Financial Forecasting","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2607.25408","title":"Context Assembly as the Controlled Variable: A Control-Theoretic View of Harness Policies for Frozen LLM Agents","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2607.25489","title":"Agentic AI in medicine: architectures, applications, evaluation, and challenges for clinical translation","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2607.27595","title":"Beyond Similarity: Grounded Agentic Extraction and Expert-Adjudicated Evaluation of Intertextuality in Classical Chinese Histories","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2608.08801","title":"IDRAAK: From Multi-Agent NLP to Few-Shot Prompting for Semantic Drift Detection in Technical Requirements","created":"2026-08-09","cited_by_count":0,"area":"agents"},{"id":"2608.31128","title":"DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening","created":"2026-08-31","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":"2609.02265","title":"CAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.04820","title":"Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.09448","title":"Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations","created":"2026-09-08","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":"2609.16309","title":"Agentic Search Spaces for Tabular Machine Learning","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.18949","title":"StableEval Arena: A Cost-Aware Agentic Benchmark for Stablecoin Price Stability Prediction","created":"2026-08-07","cited_by_count":0,"area":"agents"},{"id":"2609.19524","title":"A Unified Evaluation Framework for Trustworthy Large Language Models, Agentic AI, and Multimodal Systems","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.21997","title":"Bayesian Belief Layer for Controllable Opinion Dynamics in LLM Agents","created":"2026-09-18","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":"2609.28876","title":"Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.33401","title":"Evaluating System One Models for Agent Security Decisions: Reliability, Calibration, and Selective Automation","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.33885","title":"Prospective Interpretation Risk: Principled Communication Control Between LLMs","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.39297","title":"MiniRep: Robust Reputation-Based Aggregation for Multi-Agent Debate","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.39717","title":"Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents","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":"2610.05400","title":"CASE: Cost-Aware Stopping for Efficient Long-Video Agents","created":"2026-10-04","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}