{"total":43,"rows":[{"id":"2606.07131","title":"MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills","created":"2026-06-05","cited_by_count":19,"area":"agents"},{"id":"2503.09639","title":"Can A Society of Generative Agents Simulate Human Behavior and Inform Public Health Policy? A Case Study on Vaccine Hesitancy","created":"2025-03-12","cited_by_count":17,"area":"agents"},{"id":"2505.23559","title":"SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents","created":"2025-05-29","cited_by_count":16,"area":"agents"},{"id":"2603.19469","title":"A Framework for Formalizing LLM Agent Security","created":"2026-03-19","cited_by_count":16,"area":"agents"},{"id":"2511.20820","title":"SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models","created":"2025-11-25","cited_by_count":10,"area":"agents"},{"id":"2602.20708","title":"ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction","created":"2026-02-24","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":"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":"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":"2410.10871","title":"Applying Refusal-Vector Ablation to Llama 3.1 70B Agents","created":"2024-10-08","cited_by_count":6,"area":"agents"},{"id":"2603.06874","title":"LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models","created":"2026-03-06","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":"2505.23634","title":"MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment","created":"2025-05-29","cited_by_count":3,"area":"agents"},{"id":"2506.10622","title":"SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation","created":"2025-06-12","cited_by_count":3,"area":"agents"},{"id":"2604.03121","title":"An Independent Safety Evaluation of Kimi K2.5","created":"2026-04-03","cited_by_count":3,"area":"agents"},{"id":"2505.14215","title":"Safety Degradation in AI Agents","created":"2025-05-20","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":"2510.17431","title":"Agentic Reinforcement Learning for Search Misaligns Instruction-Tuning","created":"2025-10-20","cited_by_count":1,"area":"agents"},{"id":"2605.31075","title":"Task-Focused Memorization for Multimodal Agents","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"id":"2607.01153","title":"Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated Control","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2607.20255","title":"The Ethics of Autonomous AI Agents for Offensive Security","created":"2026-07-22","cited_by_count":1,"area":"agents"},{"id":"2607.29254","title":"Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents","created":"2026-07-31","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":"2512.09142","title":"SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation","created":"2025-12-09","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":"2605.16471","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":"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":"2605.19722","title":"Measuring Safety Alignment Effects in Autonomous Security Agents","created":"2026-05-19","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":"2607.14285","title":"ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs","created":"2026-07-15","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":"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":"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":"2609.14157","title":"When Tools Get in the Way: The Effect of Unnecessary Tool Availability on LLM Answering","created":"2026-09-12","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":"2609.17552","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":"2609.36570","title":"CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering","created":"2026-09-29","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":"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":"2610.18424","title":"Receiver Decides Agent-to-Agent Negotiations","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}