{"list":"other","total":51,"rows":[{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2507.21509","title":"Persona Vectors: Monitoring and Controlling Character Traits in Language Models","created":"2025-07-29","cited_by_count":345},{"id":"2401.11817","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","created":"2024-01-22","cited_by_count":332},{"id":"2506.06941","title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","created":"2025-06-07","cited_by_count":302},{"id":"2310.02170","title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","created":"2023-10-03","cited_by_count":290},{"id":"2506.02153","title":"Small Language Models are the Future of Agentic AI","created":"2025-06-02","cited_by_count":270},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"2012.08630","title":"Open Problems in Cooperative AI","created":"2020-12-15","cited_by_count":168},{"id":"2502.14143","title":"Multi-Agent Risks from Advanced AI","created":"2025-02-19","cited_by_count":163},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127},{"id":"2312.03664","title":"Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia","created":"2023-12-06","cited_by_count":126},{"id":"2404.16698","title":"Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents","created":"2024-04-25","cited_by_count":125},{"id":"2410.08948","title":"Emergent social conventions and collective bias in LLM populations","created":"2024-10-11","cited_by_count":123},{"id":"1710.03748","title":"Emergent Complexity via Multi-Agent Competition","created":"2017-10-10","cited_by_count":120},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99},{"id":"2502.15657","title":"Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?","created":"2025-02-21","cited_by_count":75},{"id":"2505.02077","title":"Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents","created":"2025-05-04","cited_by_count":71},{"id":"2410.04840","title":"Strong Model Collapse","created":"2024-10-07","cited_by_count":65},{"id":"2003.05004","title":"The COVID-19 Social Media Infodemic","created":"2020-03-10","cited_by_count":64},{"id":"2401.03408","title":"Escalation Risks from Language Models in Military and Diplomatic Decision-Making","created":"2024-01-07","cited_by_count":63},{"id":"2404.00806","title":"Algorithmic Collusion by Large Language Models","created":"2024-03-31","cited_by_count":62},{"id":"2504.04717","title":"Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models","created":"2025-04-07","cited_by_count":62},{"id":"2406.12934","title":"Current state of LLM Risks and AI Guardrails","created":"2024-06-16","cited_by_count":46},{"id":"2502.02649","title":"Fully Autonomous AI Agents Should Not be Developed","created":"2025-02-04","cited_by_count":45},{"id":"2507.16003","title":"Learning without training: The implicit dynamics of in-context learning","created":"2025-07-21","cited_by_count":43},{"id":"1705.08807","title":"When Will AI Exceed Human Performance? Evidence from AI Experts","created":"2017-05-24","cited_by_count":41},{"id":"2002.08506","title":"Causal Inference under Networked Interference and Intervention Policy Enhancement","created":"2020-02-20","cited_by_count":38},{"id":"2407.06813","title":"Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy","created":"2024-07-09","cited_by_count":36},{"id":"2402.14410","title":"A new sociology of humans and machines","created":"2024-02-22","cited_by_count":32},{"id":"2405.19616","title":"Easy Problems That LLMs Get Wrong","created":"2024-05-30","cited_by_count":30},{"id":"2311.00710","title":"Interactive AI Alignment: Specification, Process, and Evaluation Alignment","created":"2023-10-23","cited_by_count":22},{"id":"2405.01820","title":"Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumvention","created":"2024-05-03","cited_by_count":21},{"id":"2506.01080","title":"The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process","created":"2025-06-01","cited_by_count":21},{"id":"2507.07313","title":"Frontier LLMs Still Struggle with Simple Reasoning Tasks","created":"2025-07-09","cited_by_count":21},{"id":"2502.09369","title":"Language Agents as Digital Representatives in Collective Decision-Making","created":"2025-02-13","cited_by_count":16},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13},{"id":"2503.08223","title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","created":"2025-03-11","cited_by_count":9},{"id":"2509.10289","title":"We Need a New Ethics for a World of AI Agents","created":"2025-09-12","cited_by_count":9},{"id":"1804.06432","title":"Small vulnerable sets determine large network cascades in power grids","created":"2018-04-17","cited_by_count":8},{"id":"2406.14662","title":"Advantage Alignment Algorithms","created":"2024-06-20","cited_by_count":7},{"id":"2508.11681","title":"Future progress in artificial intelligence: A survey of expert opinion","created":"2025-08-09","cited_by_count":6},{"id":"1511.00740","title":"Learning Unfair Trading: a Market Manipulation Analysis From the Reinforcement Learning Perspective","created":"2015-11-02","cited_by_count":3},{"id":"2412.11878","title":"Using Instruction-Tuned Large Language Models to Identify Indicators of Vulnerability in Police Incident Narratives","created":"2024-12-16","cited_by_count":3},{"id":"2504.16592","title":"Algorithmic Pricing and Algorithmic Collusion","created":"2025-04-23","cited_by_count":3},{"id":"2506.12094","title":"Military AI Cyber Agents (MAICAs) Constitute a Global Threat to Critical Infrastructure","created":"2025-06-12","cited_by_count":2}],"next_cursor":null}