{"list":"other","total":75,"rows":[{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"1912.03817","title":"Machine Unlearning","created":"2019-12-09","cited_by_count":1061},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2402.17753","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","created":"2024-02-27","cited_by_count":830},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2402.01030","title":"Executable Code Actions Elicit Better LLM Agents","created":"2024-02-01","cited_by_count":564},{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2412.14093","title":"Alignment faking in large language models","created":"2024-12-18","cited_by_count":360},{"id":"2311.10537","title":"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning","created":"2023-11-16","cited_by_count":316},{"id":"2305.16367","title":"Role-Play with Large Language Models","created":"2023-05-25","cited_by_count":294},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257},{"id":"2411.10109","title":"LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals","created":"2024-11-15","cited_by_count":249},{"id":"2406.07155","title":"Scaling Large Language Model-based Multi-Agent Collaboration","created":"2024-06-11","cited_by_count":241},{"id":"2404.18231","title":"From Persona to Personalization: A Survey on Role-Playing Language Agents","created":"2024-04-28","cited_by_count":212},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205},{"id":"2404.09932","title":"Foundational Challenges in Assuring Alignment and Safety of Large Language Models","created":"2024-04-15","cited_by_count":199},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188},{"id":"2412.20138","title":"TradingAgents: Multi-Agents LLM Financial Trading Framework","created":"2024-12-28","cited_by_count":188},{"id":"2502.08691","title":"AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society","created":"2025-02-12","cited_by_count":186},{"id":"2502.14143","title":"Multi-Agent Risks from Advanced AI","created":"2025-02-19","cited_by_count":163},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157},{"id":"2410.12405","title":"ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs","created":"2024-10-16","cited_by_count":149},{"id":"2311.07590","title":"Large Language Models can Strategically Deceive their Users when Put Under Pressure","created":"2023-11-09","cited_by_count":146},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135},{"id":"2401.03729","title":"The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance","created":"2024-01-08","cited_by_count":100},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79},{"id":"2406.05804","title":"A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning","created":"2024-06-09","cited_by_count":74},{"id":"2502.03407","title":"Detecting Strategic Deception Using Linear Probes","created":"2025-02-05","cited_by_count":68},{"id":"2306.03917","title":"Turning large language models into cognitive models","created":"2023-06-06","cited_by_count":67},{"id":"1804.04268","title":"Incomplete Contracting and AI Alignment","created":"2018-04-12","cited_by_count":62},{"id":"2302.04237","title":"Black Box Adversarial Prompting for Foundation Models","created":"2023-02-08","cited_by_count":62},{"id":"2404.00806","title":"Algorithmic Collusion by Large Language Models","created":"2024-03-31","cited_by_count":62},{"id":"2102.01685","title":"Agent Incentives: A Causal Perspective","created":"2021-02-02","cited_by_count":51},{"id":"2411.02306","title":"On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback","created":"2024-11-04","cited_by_count":47},{"id":"2502.02649","title":"Fully Autonomous AI Agents Should Not be Developed","created":"2025-02-04","cited_by_count":45},{"id":"2202.10450","title":"A Survey of Ad Hoc Teamwork Research","created":"2022-02-16","cited_by_count":43},{"id":"2303.09387","title":"Characterizing Manipulation from AI Systems","created":"2023-03-16","cited_by_count":43},{"id":"2501.10114","title":"Infrastructure for AI Agents","created":"2025-01-17","cited_by_count":41},{"id":"1902.03245","title":"Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task Delegability","created":"2019-02-08","cited_by_count":36},{"id":"2006.04948","title":"AI Research Considerations for Human Existential Safety (ARCHES)","created":"2020-05-30","cited_by_count":33},{"id":"2303.08721","title":"Artificial Influence: An Analysis Of AI-Driven Persuasion","created":"2023-03-15","cited_by_count":33},{"id":"2411.03336","title":"Towards evaluations-based safety cases for AI scheming","created":"2024-10-29","cited_by_count":33},{"id":"2312.17476","title":"Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variation and Hyperparameters","created":"2023-12-29","cited_by_count":32},{"id":"2402.11863","title":"How Interpretable are Reasoning Explanations from Prompting Large Language Models?","created":"2024-02-19","cited_by_count":29},{"id":"2404.04059","title":"On the Quest for Effectiveness in Human Oversight: Interdisciplinary Perspectives","created":"2024-04-05","cited_by_count":28},{"id":"2502.19145","title":"Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems","created":"2025-02-26","cited_by_count":27},{"id":"2410.00031","title":"Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions","created":"2024-09-19","cited_by_count":26},{"id":"2303.16200","title":"Natural Selection Favors AIs over Humans","created":"2023-03-28","cited_by_count":24},{"id":"2402.08995","title":"AgentLens: Visual Analysis for Agent Behaviors in LLM-based Autonomous Systems","created":"2024-02-14","cited_by_count":23},{"id":"2402.09193","title":"(Ir)rationality and Cognitive Biases in Large Language Models","created":"2024-02-14","cited_by_count":23},{"id":"2408.06318","title":"Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example","created":"2024-08-12","cited_by_count":22},{"id":"2412.06512","title":"The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap","created":"2024-12-09","cited_by_count":20},{"id":"2501.00881","title":"Agentic Systems: A Guide to Transforming Industries with Vertical AI Agents","created":"2025-01-01","cited_by_count":20},{"id":"2503.00237","title":"Agentic AI Needs a Systems Theory","created":"2025-02-28","cited_by_count":19},{"id":"2503.12687","title":"AI Agents: Evolution, Architecture, and Real-World Applications","created":"2025-03-16","cited_by_count":19},{"id":"2405.08154","title":"LLM Theory of Mind and Alignment: Opportunities and Risks","created":"2024-05-13","cited_by_count":18},{"id":"2402.17747","title":"When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback","created":"2024-02-27","cited_by_count":17},{"id":"1811.01267","title":"Legible Normativity for AI Alignment: The Value of Silly Rules","created":"2018-11-03","cited_by_count":15},{"id":"2404.10740","title":"N-Agent Ad Hoc Teamwork","created":"2024-04-16","cited_by_count":15},{"id":"2410.07109","title":"I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy","created":"2024-10-09","cited_by_count":12},{"id":"2407.18074","title":"Principal-Agent Reinforcement Learning: Orchestrating AI Agents with Contracts","created":"2024-07-25","cited_by_count":9},{"id":"2106.06528","title":"Local Explanation of Dialogue Response Generation","created":"2021-06-11","cited_by_count":7},{"id":"2407.10735","title":"Transforming Agency. On the mode of existence of Large Language Models","created":"2024-07-15","cited_by_count":7},{"id":"2411.13904","title":"Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning","created":"2024-11-21","cited_by_count":7},{"id":"2503.13577","title":"When Should We Orchestrate Multiple Agents?","created":"2025-03-17","cited_by_count":7},{"id":"2310.15065","title":"Synergizing Human-AI Agency: A Guide of 23 Heuristics for Service Co-Creation with LLM-Based Agents","created":"2023-10-23","cited_by_count":5},{"id":"2502.10420","title":"Position: Stop Acting Like Language Model Agents Are Normal Agents","created":"2025-02-04","cited_by_count":5},{"id":"2503.15703","title":"Predicting Multi-Agent Specialization via Task Parallelizability","created":"2025-03-19","cited_by_count":5},{"id":"2209.01146","title":"Generalized Principal-Agency: Contracts, Information, Games and Beyond","created":"2022-09-02","cited_by_count":4},{"id":"2502.15278","title":"CopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion Models","created":"2025-02-21","cited_by_count":4},{"id":"2502.05986","title":"Preventing Rogue Agents Improves Multi-Agent Collaboration","created":"2025-02-09","cited_by_count":3}],"next_cursor":null}