{"list":"other","total":74,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"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":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417},{"id":"2306.13304","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","created":"2023-06-23","cited_by_count":274},{"id":"1703.04908","title":"Emergence of Grounded Compositional Language in Multi-Agent Populations","created":"2017-03-15","cited_by_count":263},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204},{"id":"1612.07182","title":"Multi-Agent Cooperation and the Emergence of (Natural) Language","created":"2016-12-21","cited_by_count":185},{"id":"2407.18219","title":"Recursive Introspection: Teaching Language Model Agents How to Self-Improve","created":"2024-07-25","cited_by_count":165},{"id":"2307.14535","title":"Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition","created":"2023-07-26","cited_by_count":159},{"id":"2305.09731","title":"What In-Context Learning \"Learns\" In-Context: Disentangling Task Recognition and Task Learning","created":"2023-05-16","cited_by_count":152},{"id":"2404.12272","title":"Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences","created":"2024-04-18","cited_by_count":144},{"id":"2404.05993","title":"AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts","created":"2024-04-09","cited_by_count":136},{"id":"2401.03428","title":"Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects","created":"2024-01-07","cited_by_count":132},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107},{"id":"2308.04026","title":"AgentSims: An Open-Source Sandbox for Large Language Model Evaluation","created":"2023-08-08","cited_by_count":88},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86},{"id":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85},{"id":"2305.03453","title":"T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answering","created":"2023-05-05","cited_by_count":60},{"id":"2308.14089","title":"MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records","created":"2023-08-27","cited_by_count":56},{"id":"2412.17481","title":"A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application","created":"2024-12-23","cited_by_count":55},{"id":"2311.16153","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","created":"2023-11-07","cited_by_count":54},{"id":"2310.02172","title":"Lyfe Agents: Generative agents for low-cost real-time social interactions","created":"2023-10-03","cited_by_count":49},{"id":"2411.04991","title":"Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives","created":"2024-11-07","cited_by_count":48},{"id":"2502.01506","title":"TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets","created":"2025-02-03","cited_by_count":48},{"id":"2405.14125","title":"ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation","created":"2024-05-23","cited_by_count":47},{"id":"2410.19609","title":"OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization","created":"2024-10-25","cited_by_count":46},{"id":"2307.05908","title":"Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding","created":"2023-07-12","cited_by_count":40},{"id":"2407.06813","title":"Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy","created":"2024-07-09","cited_by_count":36},{"id":"2306.06085","title":"Trapping LLM Hallucinations Using Tagged Context Prompts","created":"2023-06-09","cited_by_count":34},{"id":"2405.20612","title":"UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation","created":"2024-05-31","cited_by_count":31},{"id":"2303.03548","title":"Large Language Models as Zero-Shot Human Models for Human-Robot Interaction","created":"2023-03-06","cited_by_count":30},{"id":"2404.00573","title":"\"My agent understands me better\": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents","created":"2024-03-31","cited_by_count":29},{"id":"2406.18841","title":"Navigating LLM Ethics: Advancements, Challenges, and Future Directions","created":"2024-05-14","cited_by_count":28},{"id":"2307.02757","title":"Wireless Multi-Agent Generative AI: From Connected Intelligence to Collective Intelligence","created":"2023-07-06","cited_by_count":26},{"id":"2310.03659","title":"Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent Architectures","created":"2023-10-05","cited_by_count":25},{"id":"2310.14192","title":"PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation","created":"2023-10-22","cited_by_count":25},{"id":"2402.00371","title":"What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection","created":"2024-02-01","cited_by_count":25},{"id":"2309.13193","title":"SurrealDriver: Designing LLM-powered Generative Driver Agent Framework based on Human Drivers' Driving-thinking Data","created":"2023-09-22","cited_by_count":24},{"id":"2407.09893","title":"Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks","created":"2024-07-13","cited_by_count":23},{"id":"2410.02810","title":"StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking","created":"2024-09-21","cited_by_count":23},{"id":"1809.11044","title":"Relational Forward Models for Multi-Agent Learning","created":"2018-09-28","cited_by_count":21},{"id":"2402.12545","title":"TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness","created":"2024-02-19","cited_by_count":19},{"id":"2402.01737","title":"Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues","created":"2024-01-29","cited_by_count":18},{"id":"2409.10790","title":"Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering","created":"2024-09-16","cited_by_count":17},{"id":"2410.00903","title":"Causal Inference with Generative Artificial Intelligence: Application to Texts as Treatments","created":"2024-10-01","cited_by_count":16},{"id":"2401.10910","title":"Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior","created":"2024-01-09","cited_by_count":15},{"id":"2406.10291","title":"ResearchArena: Benchmarking Large Language Models' Ability to Collect and Organize Information as Research Agents","created":"2024-06-13","cited_by_count":12},{"id":"2402.02053","title":"Affordable Generative Agents","created":"2024-02-03","cited_by_count":9},{"id":"2310.01429","title":"Chatmap : Large Language Model Interaction with Cartographic Data","created":"2023-09-28","cited_by_count":7},{"id":"2304.06875","title":"nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales","created":"2023-04-14","cited_by_count":6},{"id":"2310.05853","title":"\"Mango Mango, How to Let The Lettuce Dry Without A Spinner?\": Exploring User Perceptions of Using An LLM-Based Conversational Assistant Toward Cooking Partner","created":"2023-10-09","cited_by_count":6},{"id":"2407.06146","title":"Using Grammar Masking to Ensure Syntactic Validity in LLM-based Modeling Tasks","created":"2024-07-08","cited_by_count":6},{"id":"2409.13712","title":"Good Idea or Not, Representation of LLM Could Tell","created":"2024-09-07","cited_by_count":6},{"id":"2310.12049","title":"Concept-Guided Chain-of-Thought Prompting for Pairwise Comparison Scoring of Texts with Large Language Models","created":"2023-10-18","cited_by_count":5},{"id":"2409.11636","title":"\"A Woman is More Culturally Knowledgeable than A Man?\": The Effect of Personas on Cultural Norm Interpretation in LLMs","created":"2024-09-18","cited_by_count":5},{"id":"2409.12722","title":"LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research","created":"2024-09-19","cited_by_count":5},{"id":"2410.08985","title":"Towards Trustworthy Knowledge Graph Reasoning: An Uncertainty Aware Perspective","created":"2024-10-11","cited_by_count":5},{"id":"2403.15648","title":"Unifying Large Language Model and Deep Reinforcement Learning for Human-in-Loop Interactive Socially-aware Navigation","created":"2024-03-22","cited_by_count":4},{"id":"2411.04496","title":"Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model","created":"2024-11-07","cited_by_count":3},{"id":"2401.16167","title":"\"You tell me\": A Dataset of GPT-4-Based Behaviour Change Support Conversations","created":"2024-01-29","cited_by_count":2},{"id":"2405.08032","title":"Exploring the Potential of Conversational AI Support for Agent-Based Social Simulation Model Design","created":"2024-05-12","cited_by_count":2},{"id":"2504.07385","title":"SAGE: A Search-AuGmented Evaluation of Large Language Models on Free-Form QA","created":"2025-04-10","cited_by_count":2},{"id":"1305.3842","title":"A framework for the calibration of social simulation models","created":"2013-05-16","cited_by_count":1},{"id":"2401.00503","title":"Viz: A QLoRA-based Copyright Marketplace for Legally Compliant Generative AI","created":"2023-12-31","cited_by_count":1},{"id":"2402.00260","title":"Human-mediated Large Language Models for Robotic Intervention in Children with Autism Spectrum Disorders","created":"2024-02-01","cited_by_count":1},{"id":"2406.05369","title":"Venn Diagram Prompting : Accelerating Comprehension with Scaffolding Effect","created":"2024-06-08","cited_by_count":1},{"id":"2412.18899","title":"GAI: Generative Agents for Innovation","created":"2024-12-25","cited_by_count":1}],"next_cursor":null}