{"total":30,"rows":[{"id":"2401.13178","title":"AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents","created":"2024-01-24","cited_by_count":339,"area":"agents"},{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2404.17833","title":"Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs","created":"2024-04-27","cited_by_count":22,"area":"agents"},{"id":"2508.05687","title":"Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems","created":"2025-08-06","cited_by_count":18,"area":"agents"},{"id":"2506.08972","title":"Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System","created":"2025-06-10","cited_by_count":12,"area":"agents"},{"id":"2608.02657","title":"Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States","created":"2026-08-01","cited_by_count":7,"area":"agents"},{"id":"2606.22737","title":"GroundEval: A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation","created":"2026-06-22","cited_by_count":6,"area":"agents"},{"id":"2601.22436","title":"Large Language Model Agents Are Not Always Faithful Self-Evolvers","created":"2026-01-30","cited_by_count":5,"area":"agents"},{"id":"2609.12205","title":"Plans They Abandon, Reports They Author: The Narrative Layer of Autonomous Agents","created":"2026-09-10","cited_by_count":3,"area":"agents"},{"id":"2505.02709","title":"Technical Report: Evaluating Goal Drift in Language Model Agents","created":"2025-05-05","cited_by_count":2,"area":"agents"},{"id":"2603.07202","title":"Lying to Win: Assessing LLM Deception through Human-AI Games and Parallel-World Probing","created":"2026-03-07","cited_by_count":1,"area":"agents"},{"id":"2605.09045","title":"Containment Verification: AI Safety Guarantees Independent of Alignment","created":"2026-05-09","cited_by_count":1,"area":"agents"},{"id":"2608.04265","title":"Strategic Evaluation of Planning Strategies for LLM Agents in Cyber-Physical Systems","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2609.29508","title":"Evaluation of Multi-Turn Consistency in LLM Agents: Survival Analysis and Failure-Rationale Taxonomy","created":"2026-08-26","cited_by_count":1,"area":"agents"},{"id":"2603.13791","title":"DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents","created":"2026-03-14","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":"2608.11344","title":"Governing Agentic AI in FinTech","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.20938","title":"No Judgment Without a Reason: Counterfactual Receipts for Versioned AI Evaluators","created":"2026-08-21","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":"2609.08016","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":"2609.08216","title":"Vision: Data-Centric Anchoring for Robust and Interpretable Agentic AI","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.14758","title":"Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.23215","title":"Triggers and Diagnostics for LLM-Based Interpretability Failures in Active Inference Agents","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2609.32802","title":"Re-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.36365","title":"Engineering Simplicity: Simple Mechanism Interfaces Steer LLM Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36829","title":"The Default Trap: Rethinking Plan Evaluation in Tool-Using LLM Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.36855","title":"When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.00314","title":"Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts","created":"2026-09-29","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":"2610.17444","title":"The belief-action gap in language model agents","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}