{"total":37,"rows":[{"id":"2502.08640","title":"Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs","created":"2025-02-12","cited_by_count":67,"area":"agents"},{"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":"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":"2604.01151","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":"2506.06366","title":"AI Agent Behavioral Science","created":"2025-06-04","cited_by_count":6,"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":"2401.03529","title":"Quantifying stability of non-power-seeking in artificial agents","created":"2024-01-07","cited_by_count":2,"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":"2607.05790","title":"Controlling Tool Use with Heading-Specific Activation Steering","created":"2026-07-07","cited_by_count":2,"area":"agents"},{"id":"2607.14277","title":"Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making","created":"2026-07-15","cited_by_count":2,"area":"agents"},{"id":"2608.09248","title":"Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution","created":"2026-08-10","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":"2603.05471","title":"Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval","created":"2026-03-05","cited_by_count":1,"area":"agents"},{"id":"2603.16335","title":"Behavioral Steering in a 35B MoE Language Model via SAE-Decoded Probe Vectors: One Agency Axis, Not Five Traits","created":"2026-03-17","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":"2608.25198","title":"Tunable Tool-Call Rates in LLM Agents via Representation Steering","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2609.27286","title":"Memory Control Signals Emerge Before Action in Long Horizon Agents","created":"2026-09-23","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":"2506.20062","title":"Beyond Autocomplete: Designing CopilotLens Towards Transparent and Explainable AI Coding Agents","created":"2025-06-24","cited_by_count":0,"area":"agents"},{"id":"2603.00121","title":"Graph-theoretic Agreement Framework for Multi-agent LLM Systems","created":"2026-02-23","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":"2604.06562","title":"On Emotion-Sensitive Decision Making of Small Language Model Agents","created":"2026-04-08","cited_by_count":0,"area":"agents"},{"id":"2606.00566","title":"Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models","created":"2026-05-30","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":"2608.27750","title":"The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs","created":"2026-08-27","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":"2609.14723","title":"Detecting and Localizing Segment-Level Poisoning in Multi-Source LLM-Agent Inputs","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.33039","title":"Agent Safety From Within: Detecting Harmful Trajectories from LLM Internal States","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.02702","title":"Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise","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":"2610.12445","title":"Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.19679","title":"MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}