{"total":185,"rows":[{"id":"2410.02736","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","created":"2024-10-03","cited_by_count":368,"area":null},{"id":"2410.08948","title":"Emergent social conventions and collective bias in LLM populations","created":"2024-10-11","cited_by_count":123,"area":null},{"id":"2507.15061","title":"WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization","created":"2025-07-20","cited_by_count":121,"area":null},{"id":"2404.02831","title":"Empowering Biomedical Discovery with AI Agents","created":"2024-04-03","cited_by_count":118,"area":null},{"id":"2409.20550","title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","created":"2024-09-30","cited_by_count":93,"area":null},{"id":"2406.11903","title":"A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges","created":"2024-06-15","cited_by_count":90,"area":null},{"id":"2502.18036","title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","created":"2025-02-25","cited_by_count":86,"area":null},{"id":"2408.03910","title":"CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases","created":"2024-08-07","cited_by_count":65,"area":null},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63,"area":null},{"id":"2504.15257","title":"FlowReasoner: Reinforcing Query-Level Meta-Agents","created":"2025-04-21","cited_by_count":63,"area":null},{"id":"2402.17385","title":"Determinants of LLM-assisted Decision-Making","created":"2024-02-27","cited_by_count":56,"area":null},{"id":"2406.11912","title":"AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology","created":"2024-06-16","cited_by_count":46,"area":null},{"id":"2410.11905","title":"A Scalable Communication Protocol for Networks of Large Language Models","created":"2024-10-14","cited_by_count":45,"area":null},{"id":"2505.19797","title":"The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants","created":"2025-05-26","cited_by_count":38,"area":null},{"id":"2503.05788","title":"Emergent Abilities in Large Language Models: A Survey","created":"2025-02-28","cited_by_count":37,"area":null},{"id":"2402.05138","title":"SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark","created":"2024-02-06","cited_by_count":35,"area":null},{"id":"2410.20746","title":"ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agents","created":"2024-10-28","cited_by_count":35,"area":null},{"id":"2501.05464","title":"LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models","created":"2024-12-31","cited_by_count":32,"area":null},{"id":"2409.19430","title":"'Simulacrum of Stories': Examining Large Language Models as Qualitative Research Participants","created":"2024-09-28","cited_by_count":28,"area":null},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2502.03814","title":"Large Language Models for Multi-Robot Systems: A Survey","created":"2025-02-06","cited_by_count":27,"area":null},{"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":"2505.20139","title":"StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs","created":"2025-05-26","cited_by_count":25,"area":null},{"id":"2402.01749","title":"Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models","created":"2024-01-30","cited_by_count":23,"area":null},{"id":"2502.04510","title":"Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems","created":"2025-02-06","cited_by_count":23,"area":null},{"id":"2506.01372","title":"AI Scientists Fail Without Strong Implementation Capability","created":"2025-06-02","cited_by_count":21,"area":null},{"id":"2406.01388","title":"AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2510.03346","title":"KVComm: Enabling Efficient LLM Communication through Selective KV Sharing","created":"2025-10-02","cited_by_count":18,"area":null},{"id":"2510.24697","title":"WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking","created":"2025-10-28","cited_by_count":18,"area":null},{"id":"2602.11865","title":"Intelligent AI Delegation","created":"2026-02-12","cited_by_count":18,"area":null},{"id":"2502.12435","title":"A Survey on Large Language Models for Automated Planning","created":"2025-02-18","cited_by_count":17,"area":null},{"id":"2411.04578","title":"Multi-Agents are Social Groups: Investigating Social Influence of Multiple Agents in Human-Agent Interactions","created":"2024-11-07","cited_by_count":16,"area":null},{"id":"2502.16796","title":"MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructions","created":"2025-02-24","cited_by_count":16,"area":null},{"id":"2502.01523","title":"CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering","created":"2025-02-03","cited_by_count":15,"area":null},{"id":"2507.23276","title":"How Far Are AI Scientists from Changing the World?","created":"2025-07-31","cited_by_count":15,"area":null},{"id":"2501.15361","title":"Decentralized Low-Rank Fine-Tuning of Large Language Models","created":"2025-01-26","cited_by_count":14,"area":null},{"id":"2503.14481","title":"Don't lie to your friends: Learning what you know from collaborative self-play","created":"2025-03-18","cited_by_count":14,"area":null},{"id":"2504.12714","title":"Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination","created":"2025-04-17","cited_by_count":14,"area":null},{"id":"2511.17826","title":"Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch","created":"2025-11-21","cited_by_count":14,"area":null},{"id":"2412.03338","title":"AI-Driven Day-to-Day Route Choice","created":"2024-12-04","cited_by_count":13,"area":null},{"id":"2602.09270","title":"Collective Behavior of AI Agents: the Case of Moltbook","created":"2026-02-09","cited_by_count":13,"area":null},{"id":"2508.02721","title":"Blueprint First, Model Second: A Framework for Deterministic LLM Workflow","created":"2025-08-01","cited_by_count":12,"area":null},{"id":"2602.13458","title":"MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook","created":"2026-02-13","cited_by_count":12,"area":null},{"id":"2410.13384","title":"RescueADI: Adaptive Disaster Interpretation in Remote Sensing Images with Autonomous Agents","created":"2024-10-17","cited_by_count":11,"area":null},{"id":"2410.15625","title":"Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces","created":"2024-10-21","cited_by_count":11,"area":null},{"id":"2602.03315","title":"Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity","created":"2026-02-03","cited_by_count":11,"area":null},{"id":"2402.12391","title":"Toward a Team of AI-made Scientists for Scientific Discovery from Gene Expression Data","created":"2024-02-15","cited_by_count":10,"area":null},{"id":"2408.07531","title":"Development of a Large Language Model-based Multi-Agent Clinical Decision Support System for Korean Triage and Acuity Scale (KTAS)-Based Triage and Treatment Planning in Emergency Departments","created":"2024-08-14","cited_by_count":10,"area":null},{"id":"2510.22431","title":"Hollywood Town: Long-Video Generation via Cross-Modal Multi-Agent Orchestration","created":"2025-10-25","cited_by_count":10,"area":null},{"id":"2412.07880","title":"Towards Foundation-model-based Multiagent System to Accelerate AI for Social Impact","created":"2024-12-10","cited_by_count":9,"area":null},{"id":"2506.16411","title":"When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2506.23127","title":"Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning","created":"2025-06-29","cited_by_count":9,"area":null},{"id":"2509.23023","title":"Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia","created":"2025-09-27","cited_by_count":9,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2409.07246","title":"Propaganda to Hate: A Multimodal Analysis of Arabic Memes with Multi-Agent LLMs","created":"2024-09-11","cited_by_count":8,"area":null},{"id":"2507.08892","title":"Multi-Actor Generative Artificial Intelligence as a Game Engine","created":"2025-07-10","cited_by_count":8,"area":null},{"id":"2402.19366","title":"Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2405.18272","title":"Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2502.02441","title":"LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models","created":"2025-02-04","cited_by_count":7,"area":null},{"id":"2503.02582","title":"Playing games with Large language models: Randomness and strategy","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2507.09788","title":"TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit","created":"2025-07-13","cited_by_count":7,"area":null},{"id":"2510.00510","title":"JoyAgent-JDGenie: Technical Report on the GAIA","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2606.19336","title":"Learning User Simulators with Turing Rewards","created":"2026-06-17","cited_by_count":7,"area":null},{"id":"2410.13768","title":"Rapid and Automated Alloy Design with Graph Neural Network-Powered LLM-Driven Multi-Agent Systems","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2502.11269","title":"Unlocking the Potential of Generative AI through Neuro-Symbolic Architectures: Benefits and Limitations","created":"2025-02-16","cited_by_count":6,"area":null},{"id":"2505.13523","title":"ACPs: Agent Collaboration Protocols for the Internet of Agents","created":"2025-05-18","cited_by_count":6,"area":null},{"id":"2511.04195","title":"Computational Turing Test Reveals Systematic Differences Between Human and AI Language","created":"2025-11-06","cited_by_count":6,"area":null},{"id":"2602.00854","title":"Position: Human-Centric AI Requires a Minimum Viable Level of Human Understanding","created":"2026-01-31","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2402.06049","title":"Limits of Large Language Models in Debating Humans","created":"2024-02-06","cited_by_count":5,"area":null},{"id":"2410.04054","title":"Large Language Models can Achieve Social Balance","created":"2024-10-05","cited_by_count":5,"area":null},{"id":"2412.02279","title":"A Comprehensive Evaluation of Large Language Models on Aspect-Based Sentiment Analysis","created":"2024-12-03","cited_by_count":5,"area":null},{"id":"2501.03857","title":"Progressive Document-level Text Simplification via Large Language Models","created":"2025-01-07","cited_by_count":5,"area":null},{"id":"2503.23175","title":"Large Language Models Are Unreliable for Cyber Threat Intelligence","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2504.01196","title":"$\\mu$KE: Matryoshka Unstructured Knowledge Editing of Large Language Models","created":"2025-04-01","cited_by_count":5,"area":null},{"id":"2601.18226","title":"Yunjue Agent Tech Report: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2604.10290","title":"AI Organizations are More Effective but Less Aligned than Individual Agents","created":"2026-04-11","cited_by_count":5,"area":null},{"id":"2604.13064","title":"Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub","created":"2026-03-19","cited_by_count":5,"area":null},{"id":"2410.19848","title":"Benchmarking Large Language Models for Image Classification of Marine Mammals","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2411.12808","title":"Conversational Medical AI: Ready for Practice","created":"2024-11-19","cited_by_count":4,"area":null},{"id":"2503.02399","title":"VisAgent: Narrative-Preserving Story Visualization Framework","created":"2025-03-04","cited_by_count":4,"area":null},{"id":"2503.05856","title":"This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2505.14394","title":"Knowledge Graph Based Repository-Level Code Generation","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2606.08625","title":"From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape","created":"2026-06-07","cited_by_count":4,"area":null},{"id":"2406.17809","title":"Towards a Science Exocortex","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2409.13738","title":"NLP4PBM: A Systematic Review on Process Extraction using Natural Language Processing with Rule-based, Machine and Deep Learning Methods","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2409.17655","title":"AssistantX: An LLM-Powered Proactive Assistant in Collaborative Human-Populated Environment","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2501.09444","title":"Solving the Unsolvable: Translating Case Law in Hong Kong","created":"2025-01-16","cited_by_count":3,"area":null},{"id":"2504.03029","title":"Ontologies in Design: How Imagining a Tree Reveals Possibilites and Assumptions in Large Language Models","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2505.12039","title":"AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Research","created":"2025-05-17","cited_by_count":3,"area":null},{"id":"2505.17928","title":"Towards Practical Defect-Focused Automated Code Review","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2505.21154","title":"GGBond: Growing Graph-Based AI-Agent Society for Socially-Aware Recommender Simulation","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2506.18424","title":"A Large Language Model-based Multi-Agent Framework for Analog Circuits' Sizing Relationships Extraction","created":"2025-06-23","cited_by_count":3,"area":null},{"id":"2509.12753","title":"DeltaHedge: A Multi-Agent Framework for Portfolio Options Optimization","created":"2025-09-16","cited_by_count":3,"area":null},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2510.13896","title":"GenCellAgent: Generalizable, Training-Free Cellular Image Segmentation via Large Language Model Agents","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2602.01075","title":"ConvexBench: Can LLMs Recognize Convex Functions?","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2404.00211","title":"Multi-Conditional Ranking with Large Language Models","created":"2024-03-30","cited_by_count":2,"area":null},{"id":"2410.20791","title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2503.04750","title":"AI Agents Should be Regulated Based on the Extent of Their Autonomous Operations","created":"2025-02-07","cited_by_count":2,"area":null}],"next_cursor":"100"}