{"total":35,"rows":[{"id":"2504.04072","title":"Among Us: A Sandbox for Measuring and Detecting Agentic Deception","created":"2025-04-05","cited_by_count":26,"area":"agents"},{"id":"2511.06626","title":"Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives","created":"2025-11-10","cited_by_count":15,"area":"agents"},{"id":"2602.14161","title":"When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift","created":"2026-02-15","cited_by_count":11,"area":"agents"},{"id":"2602.06286","title":"When Agents Say One Thing and Do Another: Validating Elicited Beliefs from LLMs","created":"2026-02-06","cited_by_count":10,"area":"agents"},{"id":"2605.07990","title":"Tool Calling is Linearly Readable and Steerable in Language Models","created":"2026-05-08","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":"2604.17139","title":"The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration","created":"2026-04-18","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":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2606.22953","title":"Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents","created":"2026-06-22","cited_by_count":4,"area":"agents"},{"id":"2607.06503","title":"Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade","created":"2026-07-07","cited_by_count":4,"area":"agents"},{"id":"2605.12991","title":"Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy","created":"2026-05-13","cited_by_count":3,"area":"agents"},{"id":"2606.29824","title":"Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering","created":"2026-06-29","cited_by_count":3,"area":"agents"},{"id":"2606.30449","title":"Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring","created":"2026-06-29","cited_by_count":2,"area":"agents"},{"id":"2607.04034","title":"The \"I Don't Know\" Filter: Enhancing Agentic Reliability in Function Calling","created":"2026-07-04","cited_by_count":2,"area":"agents"},{"id":"2608.10430","title":"Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique","created":"2026-08-11","cited_by_count":2,"area":"agents"},{"id":"2608.26372","title":"Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2602.08964","title":"A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents","created":"2026-02-09","cited_by_count":1,"area":"agents"},{"id":"2603.05471","title":"Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval","created":"2026-03-05","cited_by_count":1,"area":"agents"},{"id":"2603.13325","title":"Auditing Cascading Risks in Multi-Agent Systems via Semantic-Geometric Co-evolution","created":"2026-03-04","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":"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":"2606.10304","title":"MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents","created":"2026-06-09","cited_by_count":0,"area":"agents"},{"id":"2608.03071","title":"Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2608.09643","title":"Activation Probes Surface Code-Security Signals that the Model's Output Misses","created":"2026-08-10","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":"2609.03438","title":"Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI Agents","created":"2026-09-03","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":"2609.16436","title":"Interpreting and Steering LLM Agents for Social Simulations","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.37176","title":"Absorbed in Inertia: Activation Analysis for Computer-Use Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.39149","title":"Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents","created":"2026-09-30","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":"2610.12445","title":"Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.16661","title":"Structural Baselines Matter for Agent Failure Detection and Attribution","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.19679","title":"MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}