{"total":16,"rows":[{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529,"area":"agents"},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2402.07221","title":"The Reasons that Agents Act: Intention and Instrumental Goals","created":"2024-02-11","cited_by_count":23,"area":"agents"},{"id":"2512.08417","title":"Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs","created":"2025-12-09","cited_by_count":10,"area":"agents"},{"id":"2511.00810","title":"GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding","created":"2025-11-02","cited_by_count":8,"area":"agents"},{"id":"2506.02546","title":"To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems","created":"2025-06-03","cited_by_count":6,"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":"2605.03354","title":"What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis","created":"2026-05-05","cited_by_count":2,"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":"2602.05183","title":"Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning","created":"2026-02-05","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":"2606.09844","title":"The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans","created":"2026-04-26","cited_by_count":1,"area":"agents"},{"id":"2607.01047","title":"Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates","created":"2026-07-01","cited_by_count":1,"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":"2606.21732","title":"Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents","created":"2026-06-19","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"}],"next_cursor":null}