{"total":36,"rows":[{"id":"2510.05179","title":"Agentic Misalignment: How LLMs Could Be Insider Threats","created":"2025-10-05","cited_by_count":158,"area":"agents"},{"id":"2506.15740","title":"SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents","created":"2025-06-17","cited_by_count":71,"area":"agents"},{"id":"2511.09149","title":"Enabling Agents to Communicate Entirely in Latent Space","created":"2025-11-12","cited_by_count":34,"area":"agents"},{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2605.02964","title":"Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use","created":"2026-05-03","cited_by_count":31,"area":"agents"},{"id":"2507.14293","title":"WebGuard: Building a Generalizable Guardrail for Web Agents","created":"2025-07-18","cited_by_count":21,"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":"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":"2602.08235","title":"When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents","created":"2026-02-09","cited_by_count":14,"area":"agents"},{"id":"2509.05378","title":"Code Like Humans: A Multi-Agent Solution for Medical Coding","created":"2025-09-04","cited_by_count":11,"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":"2608.18398","title":"LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents","created":"2026-08-19","cited_by_count":5,"area":"agents"},{"id":"2603.28488","title":"Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification","created":"2026-03-30","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":"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":"2606.06223","title":"From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents","created":"2026-06-04","cited_by_count":3,"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":"2601.17168","title":"Interpreting Agentic Systems: Beyond Model Explanations to System-Level Accountability","created":"2026-01-23","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":"2607.18816","title":"AgentTrails: Towards Trust and Reuse for Agentic Tasks","created":"2026-07-21","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":"2607.01047","title":"Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2607.04729","title":"RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities","created":"2026-07-06","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":"2609.33495","title":"LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2608.29460","title":"Can escalation channels redirect reward hacking toward defect disclosure?","created":"2026-08-29","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":"2609.17846","title":"PrimeScientist: Strategic Allocation of Research Effort in Autonomous Research","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.18357","title":"Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents","created":"2026-09-16","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":"2610.09667","title":"Shared and structured inputs undermine collective random choice by reasoning AI agents","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.10062","title":"Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.11351","title":"Deception by Omission: Language Models Knowingly Hide Their Mistakes","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.17301","title":"The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}