{"total":28,"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":"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":"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":"2604.19775","title":"From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents","created":"2026-03-27","cited_by_count":3,"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":"2606.22673","title":"AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent","created":"2026-06-21","cited_by_count":3,"area":"agents"},{"id":"2603.12564","title":"Sell Me This Stock: Unsafe Recommendation Drift in LLM Agents","created":"2026-03-13","cited_by_count":2,"area":"agents"},{"id":"2602.06841","title":"From Features to Actions: Explainability in Traditional and Agentic AI Systems","created":"2026-02-06","cited_by_count":1,"area":"agents"},{"id":"2607.05188","title":"Latent Programming Horizons in Coding Agents","created":"2026-07-06","cited_by_count":1,"area":"agents"},{"id":"2609.15982","title":"The Router Within: Eliciting Native Skill Routing from a Frozen LLM","created":"2026-09-14","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":"2609.36642","title":"PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2605.18918","title":"ESLD (External Surrogate Latent Defense): A Latent-Space Architecture for Faster, Stronger Prompt-Injection Defense","created":"2026-05-18","cited_by_count":0,"area":"agents"},{"id":"2606.04141","title":"Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents","created":"2026-06-02","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":"2608.20393","title":"Knowledge-Graph-Gated Defactualization for Style-Controllable and Fact-Preserving Generation in Agentic Conversational AI","created":"2026-07-01","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":"2609.18357","title":"Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents","created":"2026-09-16","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":"2610.03055","title":"hacktrace: behavior-supervised detection of reward hacking during code generation","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.09624","title":"How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.17365","title":"When Goals Leak Across Relationships: How Cached Goal Representations Shape Cross-Client Decisions","created":"2026-10-12","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"}],"next_cursor":null}