{"total":78,"rows":[{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242,"area":"agents"},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2406.07155","title":"Scaling Large Language Model-based Multi-Agent Collaboration","created":"2024-06-11","cited_by_count":241,"area":"agents"},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"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,"area":"wm"},{"id":"2411.11581","title":"OASIS: Open Agent Social Interaction Simulations with One Million Agents","created":"2024-11-18","cited_by_count":132,"area":null},{"id":"2403.08715","title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents","created":"2024-03-13","cited_by_count":93,"area":"agents"},{"id":"2402.01766","title":"LLM Voting: Human Choices and AI Collective Decision Making","created":"2024-01-31","cited_by_count":48,"area":null},{"id":"2402.05699","title":"Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation","created":"2024-02-08","cited_by_count":46,"area":"alignment"},{"id":"2403.08251","title":"Emergence of Social Norms in Generative Agent Societies: Principles and Architecture","created":"2024-03-13","cited_by_count":41,"area":"agents"},{"id":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39,"area":"agents"},{"id":"2509.05830","title":"Finetuning LLMs for Human Behavior Prediction in Social Science Experiments","created":"2025-09-06","cited_by_count":39,"area":null},{"id":"2504.00218","title":"$\\textit{Agents Under Siege}$: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks","created":"2025-03-31","cited_by_count":34,"area":"agents"},{"id":"2307.12966","title":"Aligning Large Language Models with Human: A Survey","created":"2023-07-24","cited_by_count":32,"area":"alignment"},{"id":"2508.17281","title":"From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users","created":"2025-08-24","cited_by_count":32,"area":"agents"},{"id":"2412.06435","title":"Simulating Human-like Daily Activities with Desire-driven Autonomy","created":"2024-12-09","cited_by_count":30,"area":null},{"id":"2402.15527","title":"PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain","created":"2024-02-21","cited_by_count":29,"area":"mllm"},{"id":"2506.08123","title":"QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA","created":"2025-06-09","cited_by_count":28,"area":"alignment"},{"id":"2404.09127","title":"Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation","created":"2024-04-14","cited_by_count":26,"area":"agents"},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2503.13856","title":"MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation","created":"2025-03-18","cited_by_count":26,"area":"agents"},{"id":"2411.12882","title":"ProSec: Fortifying Code LLMs with Proactive Security Alignment","created":"2024-11-19","cited_by_count":25,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2406.14928","title":"Autonomous Agents for Collaborative Task under Information Asymmetry","created":"2024-06-21","cited_by_count":16,"area":"agents"},{"id":"2410.15048","title":"MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration","created":"2024-10-19","cited_by_count":16,"area":"agents"},{"id":"2504.02953","title":"Cultural Learning-Based Culture Adaptation of Language Models","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2507.11316","title":"Internal Value Alignment in Large Language Models through Controlled Value Vector Activation","created":"2025-07-15","cited_by_count":16,"area":"alignment"},{"id":"2410.15168","title":"An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making","created":"2024-10-19","cited_by_count":14,"area":"agents"},{"id":"2411.03519","title":"AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution","created":"2024-11-05","cited_by_count":14,"area":"lr"},{"id":"2501.14250","title":"Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviors","created":"2025-01-24","cited_by_count":13,"area":"safety"},{"id":"2505.19056","title":"An Embarrassingly Simple Defense Against LLM Abliteration Attacks","created":"2025-05-25","cited_by_count":13,"area":"safety"},{"id":"2410.23703","title":"OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models","created":"2024-10-31","cited_by_count":12,"area":"lr"},{"id":"2311.06330","title":"Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations","created":"2023-11-10","cited_by_count":11,"area":"agents"},{"id":"2402.00262","title":"Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective","created":"2024-02-01","cited_by_count":11,"area":"agents"},{"id":"2506.05982","title":"MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks","created":"2025-06-06","cited_by_count":11,"area":null},{"id":"2402.14963","title":"Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning","created":"2024-02-22","cited_by_count":10,"area":"lr"},{"id":"2509.16330","title":"Generalizability of Large Language Model-Based Agents: A Comprehensive Survey","created":"2025-09-19","cited_by_count":10,"area":"agents"},{"id":"2402.14228","title":"COPR: Continual Human Preference Learning via Optimal Policy Regularization","created":"2024-02-22","cited_by_count":9,"area":"alignment"},{"id":"2407.02518","title":"INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness","created":"2024-06-23","cited_by_count":8,"area":null},{"id":"2411.08243","title":"Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset","created":"2024-11-12","cited_by_count":8,"area":null},{"id":"2506.12078","title":"Modeling Earth-Scale Human-Like Societies with One Billion Agents","created":"2025-06-07","cited_by_count":8,"area":"agents"},{"id":"2410.17131","title":"Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models","created":"2024-10-22","cited_by_count":5,"area":"alignment"},{"id":"2502.10450","title":"Trustworthy AI: Safety, Bias, and Privacy -- A Survey","created":"2025-02-11","cited_by_count":5,"area":"safety"},{"id":"2506.09656","title":"Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives","created":"2025-06-11","cited_by_count":5,"area":"agents"},{"id":"2510.19299","title":"Learning to Make Friends: Coaching LLM Agents toward Emergent Social Ties","created":"2025-10-22","cited_by_count":5,"area":"agents"},{"id":"2506.24019","title":"Ella: Embodied Social Agents with Lifelong Memory","created":"2025-06-30","cited_by_count":4,"area":"agents"},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2407.21713","title":"Social Learning through Interactions with Other Agents: A Survey","created":"2024-07-31","cited_by_count":3,"area":null},{"id":"2411.04496","title":"Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model","created":"2024-11-07","cited_by_count":3,"area":"agents"},{"id":"2502.18145","title":"Carbon and Silicon, Coexist or Compete? A Survey on Human-AI Interactions in Agent-based Modeling and Simulation","created":"2025-02-25","cited_by_count":3,"area":"agents"},{"id":"2512.11844","title":"Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines","created":"2025-12-04","cited_by_count":3,"area":null},{"id":"2312.09672","title":"InstructPipe: Generating Visual Blocks Pipelines with Human Instructions and LLMs","created":"2023-12-15","cited_by_count":2,"area":null},{"id":"2408.04522","title":"Compromesso! Italian Many-Shot Jailbreaks Undermine the Safety of Large Language Models","created":"2024-08-08","cited_by_count":2,"area":"safety"},{"id":"2410.18935","title":"Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2505.09938","title":"Design and Evaluation of Generative Agent-based Platform for Human-Assistant Interaction Research: A Tale of 10 User Studies","created":"2025-05-15","cited_by_count":2,"area":"agents"},{"id":"2510.01164","title":"Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare","created":"2025-10-01","cited_by_count":2,"area":"agents"},{"id":"2510.01342","title":"Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach","created":"2025-10-01","cited_by_count":2,"area":"safety"},{"id":"2510.23245","title":"Multi-Stakeholder Alignment in LLM-Powered Collaborative AI Systems: A Multi-Agent Framework for Intelligent Tutoring","created":"2025-10-27","cited_by_count":2,"area":"agents"},{"id":"2602.00685","title":"HumanStudy-Bench: Towards AI Agent Design for Participant Simulation","created":"2026-01-31","cited_by_count":2,"area":"agents"},{"id":"2402.06654","title":"Conversational Crowdsensing: A Parallel Intelligence Powered Novel Sensing Approach","created":"2024-02-04","cited_by_count":1,"area":null},{"id":"2410.12123","title":"Large Language Models, and LLM-Based Agents, Should Be Used to Enhance the Digital Public Sphere","created":"2024-10-15","cited_by_count":1,"area":"agents"},{"id":"2506.21961","title":"PapersPlease: A Benchmark for Evaluating Motivational Values of Large Language Models Based on ERG Theory","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2511.03271","title":"Let the Bees Find the Weak Spots: A Path Planning Perspective on Multi-Turn Jailbreak Attacks against LLMs","created":"2025-11-05","cited_by_count":1,"area":"safety"},{"id":"2605.07462","title":"The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2607.14485","title":"Step-Level Preference Learning for Generative Agents in Social Simulations","created":"2026-07-16","cited_by_count":1,"area":"agents"},{"id":"2410.22041","title":"An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling","created":"2024-10-29","cited_by_count":0,"area":"agents"},{"id":"2506.10020","title":"From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment","created":"2025-06-07","cited_by_count":0,"area":"alignment"},{"id":"2510.06225","title":"Generalized Multi-agent Social Simulation Framework","created":"2025-09-26","cited_by_count":0,"area":"agents"},{"id":"2510.25426","title":"Implicature in Interaction: Understanding Implicature Improves Alignment in Human-LLM Interaction","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2603.11333","title":"LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platforms","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.12195","title":"Representing expertise accelerates learning from pedagogical interaction data","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2606.16562","title":"MIRAGE: Auditing Anti-Muslim Bias in Frontier LLMs Across Reasoning, Agentic, and Time-Coupled Conditions","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2608.00134","title":"Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"id":"2608.10327","title":"Toward a Theory of Value in AI Alignment","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.27910","title":"AI Alignment through a Game-theoretic Lens: A Survey","created":"2026-08-28","cited_by_count":0,"area":"alignment"}],"next_cursor":null}