{"total":17,"rows":[{"id":"2510.05179","title":"Agentic Misalignment: How LLMs Could Be Insider Threats","created":"2025-10-05","cited_by_count":158,"area":"agents"},{"id":"2404.14394","title":"A Multimodal Automated Interpretability Agent","created":"2024-04-22","cited_by_count":63,"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":"2407.12161","title":"Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent","created":"2024-07-16","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":"2601.23211","title":"Multi-Agent Systems Should be Treated as Principal-Agent Problems","created":"2026-01-30","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":"2603.20101","title":"Pitfalls in Evaluating Interpretability Agents","created":"2026-03-20","cited_by_count":2,"area":"agents"},{"id":"2605.03354","title":"What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis","created":"2026-05-05","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":"2604.04157","title":"Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents","created":"2026-04-05","cited_by_count":1,"area":"agents"},{"id":"2605.26343","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2606.24026","title":"Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?","created":"2026-06-23","cited_by_count":1,"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":"2606.14831","title":"Is Your Agent Playing Dead? Deployed LLM Agents Exhibit Constraint-Evasive Fabrication and Thanatosis","created":"2026-06-12","cited_by_count":0,"area":"agents"},{"id":"2609.22712","title":"Trustworthy Agentic AI: Failure Modes, Mitigation Strategies, and a Lifecycle Framework for Autonomous LLM Systems","created":"2026-09-19","cited_by_count":0,"area":"agents"}],"next_cursor":null}