{"total":91,"rows":[{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2406.00244","title":"Controlling Large Language Model Agents with Entropic Activation Steering","created":"2024-06-01","cited_by_count":29,"area":"agents"},{"id":"2509.10723","title":"Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight","created":"2025-09-12","cited_by_count":16,"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":"2504.20082","title":"Evolution of AI in Education: Agentic Workflows","created":"2025-04-25","cited_by_count":13,"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":"2604.23338","title":"A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework","created":"2026-04-25","cited_by_count":11,"area":"agents"},{"id":"2603.00829","title":"Constitutional Black-Box Monitoring for Scheming in LLM Agents","created":"2026-02-28","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":"2412.15504","title":"Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework","created":"2024-12-20","cited_by_count":8,"area":"agents"},{"id":"2601.08462","title":"M3-BENCH: Process-Aware Evaluation of LLM Agents' Social Behaviors in Mixed-Motive Games","created":"2026-01-13","cited_by_count":8,"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":"2606.09071","title":"REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces","created":"2026-06-08","cited_by_count":7,"area":"agents"},{"id":"2404.15974","title":"A Human-Computer Collaborative Tool for Training a Single Large Language Model Agent into a Network through Few Examples","created":"2024-04-24","cited_by_count":5,"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":"2605.17467","title":"VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems","created":"2026-05-17","cited_by_count":5,"area":"agents"},{"id":"2608.18398","title":"LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents","created":"2026-08-19","cited_by_count":5,"area":"agents"},{"id":"2602.01405","title":"Feedback by Design: Understanding and Overcoming User Feedback Barriers in Conversational Agents","created":"2026-02-01","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":"2605.12004","title":"Learning Agentic Policy from Action Guidance","created":"2026-05-12","cited_by_count":4,"area":"agents"},{"id":"2609.20812","title":"Quantifying Overclaiming Propensity in Frontier LLM Agents","created":"2026-09-17","cited_by_count":4,"area":"agents"},{"id":"2601.23211","title":"Multi-Agent Systems Should be Treated as Principal-Agent Problems","created":"2026-01-30","cited_by_count":3,"area":"agents"},{"id":"2602.16844","title":"Overseeing Agents Without Constant Oversight: Challenges and Opportunities","created":"2026-02-18","cited_by_count":3,"area":"agents"},{"id":"2602.16943","title":"Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents","created":"2026-02-18","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":"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":"2506.02739","title":"Why do AI agents communicate in human language?","created":"2025-06-03","cited_by_count":2,"area":"agents"},{"id":"2512.02530","title":"Aetheria: A multimodal interpretable content safety framework based on multi-agent debate and collaboration","created":"2025-12-02","cited_by_count":2,"area":"agents"},{"id":"2602.00428","title":"When Agents \"Misremember\" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems","created":"2026-01-31","cited_by_count":2,"area":"agents"},{"id":"2603.05872","title":"Evolving Deception: When Agents Evolve, Deception Wins","created":"2026-03-06","cited_by_count":2,"area":"agents"},{"id":"2605.01329","title":"Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents","created":"2026-05-02","cited_by_count":2,"area":"agents"},{"id":"2606.00497","title":"\"I Strongly Suspect This Website Is a Scam\": Benchmarking PII Leakage and Detection without Defense in Autonomous Web Agents","created":"2026-05-30","cited_by_count":2,"area":"agents"},{"id":"2606.18142","title":"Your AI Travel Agent Would Book You a Bullfight: An Agentic Benchmark for Implicit Animal Welfare in Frontier AI Models","created":"2026-06-16","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":"2608.14825","title":"Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce","created":"2026-08-14","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":"2410.12123","title":"Large Language Models, and LLM-Based Agents, Should Be Used to Enhance the Digital Public Sphere","created":"2024-10-15","cited_by_count":1,"area":"agents"},{"id":"2509.16666","title":"Robust Native Language Identification through Agentic Decomposition","created":"2025-09-20","cited_by_count":1,"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":"2606.02380","title":"SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"id":"2606.18671","title":"HANSEL: Extracting Breadcrumbs from Web Agent Trajectories for Interactive Verification","created":"2026-06-17","cited_by_count":1,"area":"agents"},{"id":"2607.19449","title":"Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents","created":"2026-07-21","cited_by_count":1,"area":"agents"},{"id":"2607.21518","title":"Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation","created":"2026-07-23","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":"2608.20670","title":"Why2Speak: Faithful Reasoning for Abstaining Action Policies","created":"2026-08-21","cited_by_count":1,"area":"agents"},{"id":"2609.08589","title":"The Unreliable Progress Bar: Can LLM Agents Reliably Report Task Progress Throughout Execution?","created":"2026-09-08","cited_by_count":1,"area":"agents"},{"id":"2609.13529","title":"Generative Interpretability via Scalable Neuro-Symbolic Models","created":"2026-09-11","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":"2609.33495","title":"LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2609.39050","title":"Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2507.13175","title":"Black Box Deployed -- Functional Criteria for Artificial Moral Agents in the LLM Era","created":"2025-07-17","cited_by_count":0,"area":"agents"},{"id":"2511.09178","title":"Perspectives on a Reliability Monitoring Framework for Agentic AI Systems","created":"2025-11-12","cited_by_count":0,"area":"agents"},{"id":"2601.14566","title":"SCSimulator: An Exploratory Visual Analytics Framework for Partner Selection in Supply Chains through LLM-driven Multi-Agent Simulation","created":"2026-01-21","cited_by_count":0,"area":"agents"},{"id":"2603.05028","title":"Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure","created":"2026-03-05","cited_by_count":0,"area":"agents"},{"id":"2603.07848","title":"Intentional Deception as Controllable Capability in LLM Agents","created":"2026-03-08","cited_by_count":0,"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":"2604.07745","title":"The Cartesian Cut in Agentic AI","created":"2026-04-09","cited_by_count":0,"area":"agents"},{"id":"2605.12087","title":"Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic Systems","created":"2026-05-12","cited_by_count":0,"area":"agents"},{"id":"2605.12694","title":"Agentic Interpretation: Lattice-Structured Evidence for LLM-Based Program Analysis","created":"2026-05-12","cited_by_count":0,"area":"agents"},{"id":"2605.25981","title":"AgentDiff: Meaning-Bearing Rewrites Trigger Deeper Divergence than Presentation Changes in LLM Agents","created":"2026-05-25","cited_by_count":0,"area":"agents"},{"id":"2605.29251","title":"Provably Secure Agent Guardrail","created":"2026-05-28","cited_by_count":0,"area":"agents"},{"id":"2606.10747","title":"The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment","created":"2026-06-09","cited_by_count":0,"area":"agents"},{"id":"2606.13405","title":"Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda","created":"2026-06-11","cited_by_count":0,"area":"agents"},{"id":"2607.01808","title":"Archer: Towards Agentic Review for Compiler Optimizations","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2608.08164","title":"STEMMA: An Adversarial Multi-Agent Framework for Evaluating Self-Identity Consistency in LLMs","created":"2026-08-08","cited_by_count":0,"area":"agents"},{"id":"2608.11033","title":"Who Are You Explaining To? A Multi-Agent System for Audience-Aware XAI Narratives","created":"2026-08-11","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":"2608.18846","title":"ORBITER: Conflict-Aware Decision-Making for Agentic Last-Mile Delivery","created":"2026-08-19","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":"2609.02265","title":"CAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.05975","title":"Intent Drift at SME Scale: Deployment Practice, Not Model Capability, Determines Agentic Compliance","created":"2026-09-05","cited_by_count":0,"area":"agents"},{"id":"2609.07573","title":"From Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interaction","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":"2609.08126","title":"SchemeArena: Factorized Stress Testing of Scheming in LLM Agents","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.14422","title":"Safety Signals to Verify NetOps Agents with Action-Level Granularity","created":"2026-09-13","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":"2609.22712","title":"Trustworthy Agentic AI: Failure Modes, Mitigation Strategies, and a Lifecycle Framework for Autonomous LLM Systems","created":"2026-09-19","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":"2609.27639","title":"Agent-based Modeling: Equilibrium, Echo Chambers, and Efficiency in Hybrid Coevolutionary Opinion Games","created":"2026-09-23","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":"2609.35279","title":"Measuring Collapse and Correction in Homogeneous-Panel LLM Debate","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":"2610.00961","title":"Cybernetic and Epistemic: A Missing Vocabulary for Trustworthy Agentic Delegation","created":"2026-10-01","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":"2610.15258","title":"Sequent-Prover: Training Agents for Formal, Checkable SMT-based Reasoning","created":"2026-10-11","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"},{"id":"2610.18424","title":"Receiver Decides Agent-to-Agent Negotiations","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}