{"total":68,"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":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2605.21384","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","created":"2026-05-20","cited_by_count":28,"area":"agents"},{"id":"2512.13526","title":"Async Control: Stress-testing Asynchronous Control Measures for LLM Agents","created":"2025-12-15","cited_by_count":22,"area":"agents"},{"id":"2504.05259","title":"How to evaluate control measures for LLM agents? A trajectory from today to superintelligence","created":"2025-04-07","cited_by_count":20,"area":"agents"},{"id":"2603.15714","title":"How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition","created":"2026-03-16","cited_by_count":17,"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":"2603.04474","title":"From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration","created":"2026-03-04","cited_by_count":14,"area":"agents"},{"id":"2505.17767","title":"Position: The Real Barrier to LLM Agent Usability is Agentic ROI","created":"2025-05-23","cited_by_count":12,"area":"agents"},{"id":"2605.08715","title":"AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems","created":"2026-05-09","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":"2606.26300","title":"The Verification Horizon: No Silver Bullet for Coding Agent Rewards","created":"2026-06-24","cited_by_count":8,"area":"agents"},{"id":"2604.01151","title":"Detecting Multi-Agent Collusion Through Multi-Agent Interpretability","created":"2026-04-01","cited_by_count":7,"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":"2510.05192","title":"From surveillance to signalling: escalation channels as environmental controls for agentic AI","created":"2025-10-06","cited_by_count":6,"area":"agents"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2606.28425","title":"Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems","created":"2026-06-25","cited_by_count":5,"area":"agents"},{"id":"2607.02514","title":"Distributed Attacks in Persistent-State AI Control","created":"2026-07-02","cited_by_count":5,"area":"agents"},{"id":"2608.23564","title":"SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?","created":"2026-08-24","cited_by_count":5,"area":"agents"},{"id":"2509.23694","title":"SafeSearch: Automated Red-Teaming of LLM-Based Search Agents","created":"2025-09-28","cited_by_count":4,"area":"agents"},{"id":"2606.28430","title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested","created":"2026-06-26","cited_by_count":4,"area":"agents"},{"id":"2607.25152","title":"When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops","created":"2026-07-27","cited_by_count":4,"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":"2608.12841","title":"AQuA: Recursively Self-Improving Quantitative Trading Research Agents","created":"2026-08-13","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"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":"2609.24967","title":"Emergent Collusion in Long-Horizon LLM Agent Interaction","created":"2026-09-21","cited_by_count":2,"area":"agents"},{"id":"2609.28614","title":"Reward Hacking Challenges Oversight of Autonomous Research Agents","created":"2026-09-23","cited_by_count":2,"area":"agents"},{"id":"2506.13774","title":"Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values","created":"2025-06-08","cited_by_count":1,"area":"agents"},{"id":"2602.04197","title":"From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents","created":"2026-02-04","cited_by_count":1,"area":"agents"},{"id":"2602.05066","title":"Bypassing AI Control Protocols via Agent-as-a-Proxy Attacks","created":"2026-02-04","cited_by_count":1,"area":"agents"},{"id":"2607.18575","title":"RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery","created":"2026-07-20","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":"2609.01491","title":"GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions","created":"2026-09-01","cited_by_count":1,"area":"agents"},{"id":"2609.36490","title":"LLMs Learn to Evade Latent Monitors from Prior Feedback Alone","created":"2026-09-29","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":"2610.01023","title":"Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents","created":"2026-10-01","cited_by_count":1,"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":"2603.13791","title":"DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents","created":"2026-03-14","cited_by_count":0,"area":"agents"},{"id":"2607.18064","title":"Autoresearch with Coding Agents: Generalizers and Metric-Maximizers on Quran Recitation Data","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2608.11274","title":"Agent Safety Should Be a Runtime Contract","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.27348","title":"INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment","created":"2026-08-27","cited_by_count":0,"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":"2609.02371","title":"Diagnosing with Insights: Structured Analysis of Agent Failures via Behavioral Abstractions","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.03035","title":"You Can't Escape Your Own Activations : Evaluation Awareness and Multi-Agent Monitoring","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.07910","title":"PRIMUS: Identity, Governance, and Verification for Multi-Agent Federations","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":"2609.17552","title":"Does Moral Reasoning Training Help or Hurt? Red-Teaming RL-Trained Ethical Agents with Persona Attacks","created":"2026-07-16","cited_by_count":0,"area":"agents"},{"id":"2609.23700","title":"When the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating Systems","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.27542","title":"Control-Token Injection Suppresses Chain-of-Thought and Defeats Reasoning-Based Oversight in Tool-Using Agents","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.28900","title":"Codetta: High-Capacity, Keyless, and Undetectable Multi-Agent Collusion","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.30266","title":"LLM Agents Can Easily Tamper With Their Own Traces","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.32021","title":"SilentCall: Hidden Tool-Call Backdoors in Open-Weight Agents, and How to Catch Them","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2610.02952","title":"GTDD: Generative Test-Driven Development for AI Coding Agents with Adversarial Testing","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.03055","title":"hacktrace: behavior-supervised detection of reward hacking during code generation","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.06204","title":"Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.06576","title":"Before Agent Tells The Lie: Has Deception Already Been Represented?","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.07089","title":"Towards a Unified Misuse Monitoring Benchmark","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.09159","title":"SpecGuard: Proving a Task Is Broken Before the Agent Cheats","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.10942","title":"StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.11559","title":"SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.12445","title":"Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception","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"},{"id":"2610.17724","title":"Evidence-First Agentic Verification","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.17727","title":"SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}