{"total":58,"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":"2502.12961","title":"Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger","created":"2025-02-18","cited_by_count":30,"area":"agents"},{"id":"2406.00244","title":"Controlling Large Language Model Agents with Entropic Activation Steering","created":"2024-06-01","cited_by_count":29,"area":"agents"},{"id":"2511.04847","title":"Test-Time Adaptation for LLM Agents via Environment Interaction","created":"2025-11-06","cited_by_count":20,"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":"2509.13588","title":"CoBRA: Programming Cognitive Bias in Social Agents Using Classic Social Science Experiments","created":"2025-09-16","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":"2605.14038","title":"Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2606.22864","title":"When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents","created":"2026-06-22","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":"2412.16325","title":"Towards Safe and Honest AI Agents with Neural Self-Other Overlap","created":"2024-12-20","cited_by_count":6,"area":"agents"},{"id":"2601.21742","title":"Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems","created":"2026-01-29","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":"2501.19398","title":"Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game","created":"2025-01-31","cited_by_count":5,"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":"2407.12161","title":"Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent","created":"2024-07-16","cited_by_count":4,"area":"agents"},{"id":"2509.04794","title":"Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effects","created":"2025-09-05","cited_by_count":4,"area":"agents"},{"id":"2604.03870","title":"Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs","created":"2026-04-04","cited_by_count":4,"area":"agents"},{"id":"2605.01555","title":"Automated Interpretability and Feature Discovery in Language Models with Agents","created":"2026-05-02","cited_by_count":4,"area":"agents"},{"id":"2605.24941","title":"Memory-Induced Tool-Drift in LLM Agents","created":"2026-05-24","cited_by_count":4,"area":"agents"},{"id":"2505.10670","title":"Interpretable Risk Mitigation in LLM Agent Systems","created":"2025-05-15","cited_by_count":3,"area":"agents"},{"id":"2603.00113","title":"AI Agents Alone Are Not (Yet) Sufficient for Social Simulation","created":"2026-02-19","cited_by_count":3,"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":"2503.12722","title":"Identifying Cooperative Personalities in Multi-agent Contexts through Personality Steering with Representation Engineering","created":"2025-03-17","cited_by_count":2,"area":"agents"},{"id":"2606.07818","title":"Representational Similarity and Model Behavior in Multi-Agent Interaction","created":"2026-06-05","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":"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":"2510.17431","title":"Agentic Reinforcement Learning for Search Misaligns Instruction-Tuning","created":"2025-10-20","cited_by_count":1,"area":"agents"},{"id":"2512.04691","title":"Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective","created":"2025-12-04","cited_by_count":1,"area":"agents"},{"id":"2608.00023","title":"Role Steering of Language Models for Social Simulations","created":"2026-07-09","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":"2609.36490","title":"LLMs Learn to Evade Latent Monitors from Prior Feedback Alone","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2610.00400","title":"Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2511.09178","title":"Perspectives on a Reliability Monitoring Framework for Agentic AI Systems","created":"2025-11-12","cited_by_count":0,"area":"agents"},{"id":"2602.22070","title":"Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human Experts","created":"2026-02-25","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":"2605.02914","title":"When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models","created":"2026-04-08","cited_by_count":0,"area":"agents"},{"id":"2605.16471","title":"From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI","created":"2026-05-15","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":"2608.20393","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":"2608.25711","title":"Reassembling Distributed Risk: Trajectory-Conditioned Action Generation for Multi-Turn Agent Safety","created":"2026-08-26","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":"2609.14723","title":"Detecting and Localizing Segment-Level Poisoning in Multi-Source LLM-Agent Inputs","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.17552","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":"2609.19203","title":"Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.34372","title":"PersMem: Internalizing Personality into Dual-Pathway Memory for LLM Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36138","title":"When Does Correction Become Repair? Mechanistic Auditing of Internal Interventions in Tool-Using LLMs","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36570","title":"CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.39107","title":"MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models","created":"2026-09-30","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":"2610.02413","title":"Prompted to Discriminate: Generalizing Malicious-Input Probes in the Wild","created":"2026-10-01","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":"2610.17301","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":"2610.19679","title":"MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}