{"list":"other","total":135,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2502.12110","title":"A-MEM: Agentic Memory for LLM Agents","created":"2025-02-17","cited_by_count":1063},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658},{"id":"2302.11382","title":"A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT","created":"2023-02-21","cited_by_count":619},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260},{"id":"2306.02224","title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","created":"2023-06-04","cited_by_count":255},{"id":"2411.04468","title":"Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks","created":"2024-11-07","cited_by_count":232},{"id":"2307.08177","title":"Using an LLM to Help With Code Understanding","created":"2023-07-17","cited_by_count":228},{"id":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205},{"id":"2410.08164","title":"Agent S: An Open Agentic Framework that Uses Computers Like a Human","created":"2024-10-10","cited_by_count":187},{"id":"2308.15272","title":"AutoDroid: LLM-powered Task Automation in Android","created":"2023-08-29","cited_by_count":184},{"id":"2505.10468","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","created":"2025-05-15","cited_by_count":169},{"id":"2502.14143","title":"Multi-Agent Risks from Advanced AI","created":"2025-02-19","cited_by_count":163},{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162},{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149},{"id":"2203.06566","title":"PromptChainer: Chaining Large Language Model Prompts through Visual Programming","created":"2022-03-13","cited_by_count":134},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126},{"id":"2404.16811","title":"Make Your LLM Fully Utilize the Context","created":"2024-04-25","cited_by_count":119},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111},{"id":"2408.15978","title":"WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration","created":"2024-08-28","cited_by_count":101},{"id":"2403.16971","title":"AIOS: LLM Agent Operating System","created":"2024-03-25","cited_by_count":97},{"id":"2411.07781","title":"RedCode: Risky Code Execution and Generation Benchmark for Code Agents","created":"2024-11-12","cited_by_count":90},{"id":"2407.20859","title":"Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification","created":"2024-07-30","cited_by_count":81},{"id":"2309.14459","title":"Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces","created":"2023-09-25","cited_by_count":72},{"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":"2310.15100","title":"LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis","created":"2023-10-23","cited_by_count":70},{"id":"2309.09919","title":"Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents","created":"2023-09-18","cited_by_count":69},{"id":"2303.07839","title":"ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design","created":"2023-03-11","cited_by_count":66},{"id":"2410.03981","title":"A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages","created":"2024-10-04","cited_by_count":66},{"id":"2306.14924","title":"LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding","created":"2023-06-23","cited_by_count":64},{"id":"2410.21965","title":"SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types","created":"2024-10-29","cited_by_count":60},{"id":"2309.14049","title":"How Novices Use LLM-Based Code Generators to Solve CS1 Coding Tasks in a Self-Paced Learning Environment","created":"2023-09-25","cited_by_count":56},{"id":"2409.01227","title":"Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference","created":"2024-09-02","cited_by_count":53},{"id":"2503.12188","title":"Multi-Agent Systems Execute Arbitrary Malicious Code","created":"2025-03-15","cited_by_count":53},{"id":"2404.10100","title":"LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation","created":"2024-04-15","cited_by_count":49},{"id":"2407.21579","title":"A Performance Study of LLM-Generated Code on Leetcode","created":"2024-07-31","cited_by_count":49},{"id":"2505.16944","title":"AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios","created":"2025-05-22","cited_by_count":49},{"id":"2312.15224","title":"LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination","created":"2023-12-23","cited_by_count":48},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47},{"id":"2404.07362","title":"\"We Need Structured Output\": Towards User-centered Constraints on Large Language Model Output","created":"2024-04-10","cited_by_count":46},{"id":"2410.10630","title":"Thinking LLMs: General Instruction Following with Thought Generation","created":"2024-10-14","cited_by_count":45},{"id":"2504.21034","title":"SAGA: A Security Architecture for Governing AI Agentic Systems","created":"2025-04-27","cited_by_count":45},{"id":"2408.16498","title":"A Survey on Evaluating Large Language Models in Code Generation Tasks","created":"2024-08-29","cited_by_count":44},{"id":"2303.08769","title":"Prompting Large Language Models With the Socratic Method","created":"2023-02-17","cited_by_count":43},{"id":"2505.07782","title":"MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering","created":"2025-05-12","cited_by_count":41},{"id":"2405.18649","title":"LeDex: Training LLMs to Better Self-Debug and Explain Code","created":"2024-05-28","cited_by_count":40},{"id":"2408.01703","title":"WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization","created":"2024-08-03","cited_by_count":39},{"id":"2502.13681","title":"Repo2Run: Automated Building Executable Environment for Code Repository at Scale","created":"2025-02-19","cited_by_count":39},{"id":"2404.00405","title":"A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration","created":"2024-03-30","cited_by_count":38},{"id":"2405.02213","title":"Automatic Programming: Large Language Models and Beyond","created":"2024-05-03","cited_by_count":36},{"id":"2405.04798","title":"From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control","created":"2024-05-08","cited_by_count":35},{"id":"2406.12692","title":"MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL","created":"2024-06-18","cited_by_count":35},{"id":"2409.10737","title":"AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing","created":"2024-09-16","cited_by_count":35},{"id":"2501.16150","title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","created":"2025-01-27","cited_by_count":34},{"id":"2502.18658","title":"Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support","created":"2025-02-25","cited_by_count":34},{"id":"2504.18875","title":"Generative to Agentic AI: Survey, Conceptualization, and Challenges","created":"2025-04-26","cited_by_count":33},{"id":"2312.03543","title":"GPT-4 Enhanced Multimodal Grounding for Autonomous Driving: Leveraging Cross-Modal Attention with Large Language Models","created":"2023-12-06","cited_by_count":32},{"id":"2404.04442","title":"Exploring Autonomous Agents through the Lens of Large Language Models: A Review","created":"2024-04-05","cited_by_count":31},{"id":"2505.07176","title":"Internet of Agents: Fundamentals, Applications, and Challenges","created":"2025-05-12","cited_by_count":31},{"id":"2504.21848","title":"Characterizing AI Agents for Alignment and Governance","created":"2025-04-30","cited_by_count":30},{"id":"2304.08191","title":"A study on Prompt Design, Advantages and Limitations of ChatGPT for Deep Learning Program Repair","created":"2023-04-17","cited_by_count":26},{"id":"2503.16734","title":"Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models","created":"2025-03-20","cited_by_count":26},{"id":"2403.08299","title":"AutoDev: Automated AI-Driven Development","created":"2024-03-13","cited_by_count":24},{"id":"2409.08775","title":"What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use","created":"2024-09-13","cited_by_count":24},{"id":"2505.13941","title":"MLZero: A Multi-Agent System for End-to-end Machine Learning Automation","created":"2025-05-20","cited_by_count":24},{"id":"2504.21030","title":"Advancing Multi-Agent Systems Through Model Context Protocol: Architecture, Implementation, and Applications","created":"2025-04-26","cited_by_count":23},{"id":"2404.14459","title":"LLMs in Web Development: Evaluating LLM-Generated PHP Code Unveiling Vulnerabilities and Limitations","created":"2024-04-21","cited_by_count":22},{"id":"2404.18496","title":"AI-powered Code Review with LLMs: Early Results","created":"2024-04-29","cited_by_count":22},{"id":"2406.10101","title":"Requirements are All You Need: From Requirements to Code with LLMs","created":"2024-06-14","cited_by_count":22},{"id":"2502.14000","title":"Human-Artificial Interaction in the Age of Agentic AI: A System-Theoretical Approach","created":"2025-02-19","cited_by_count":22},{"id":"2501.00881","title":"Agentic Systems: A Guide to Transforming Industries with Vertical AI Agents","created":"2025-01-01","cited_by_count":20},{"id":"2502.13311","title":"Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors","created":"2025-02-18","cited_by_count":20},{"id":"2406.12513","title":"Can We Trust Large Language Models Generated Code? A Framework for In-Context Learning, Security Patterns, and Code Evaluations Across Diverse LLMs","created":"2024-06-18","cited_by_count":19},{"id":"2503.00237","title":"Agentic AI Needs a Systems Theory","created":"2025-02-28","cited_by_count":19},{"id":"2312.00763","title":"Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses","created":"2023-12-01","cited_by_count":18},{"id":"2410.12375","title":"PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking","created":"2024-10-16","cited_by_count":17},{"id":"2405.17915","title":"Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language Models","created":"2024-05-28","cited_by_count":16},{"id":"2408.03876","title":"From Data to Story: Towards Automatic Animated Data Video Creation with LLM-based Multi-Agent Systems","created":"2024-08-07","cited_by_count":16},{"id":"2505.12786","title":"Forewarned is Forearmed: A Survey on Large Language Model-based Agents in Autonomous Cyberattacks","created":"2025-05-19","cited_by_count":16},{"id":"2501.06781","title":"Eliza: A Web3 friendly AI Agent Operating System","created":"2025-01-12","cited_by_count":15},{"id":"2504.20117","title":"ResearchCodeAgent: An LLM Multi-Agent System for Automated Codification of Research Methodologies","created":"2025-04-28","cited_by_count":15},{"id":"2403.19876","title":"\"I'm categorizing LLM as a productivity tool\": Examining ethics of LLM use in HCI research practices","created":"2024-03-28","cited_by_count":14},{"id":"2501.01264","title":"ProgCo: Program Helps Self-Correction of Large Language Models","created":"2025-01-02","cited_by_count":14},{"id":"2503.06745","title":"Beyond Black-Box Benchmarking: Observability, Analytics, and Optimization of Agentic Systems","created":"2025-03-09","cited_by_count":14},{"id":"2503.12651","title":"VeriLA: A Human-Centered Evaluation Framework for Interpretable Verification of LLM Agent Failures","created":"2025-03-16","cited_by_count":14},{"id":"2503.21720","title":"Collab: Controlled Decoding using Mixture of Agents for LLM Alignment","created":"2025-03-27","cited_by_count":14},{"id":"2505.16988","title":"MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems","created":"2025-05-22","cited_by_count":14},{"id":"2402.05650","title":"Rocks Coding, Not Development--A Human-Centric, Experimental Evaluation of LLM-Supported SE Tasks","created":"2024-02-08","cited_by_count":13},{"id":"2503.06911","title":"Beyond Code Generation: LLM-supported Exploration of the Program Design Space","created":"2025-03-10","cited_by_count":13},{"id":"2504.20082","title":"Evolution of AI in Education: Agentic Workflows","created":"2025-04-25","cited_by_count":13},{"id":"2504.02623","title":"Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions","created":"2025-04-03","cited_by_count":12},{"id":"1310.2431","title":"Practical Verification of Decision-Making in Agent-Based Autonomous Systems","created":"2013-10-09","cited_by_count":11},{"id":"2404.03823","title":"An Investigation into Misuse of Java Security APIs by Large Language Models","created":"2024-04-04","cited_by_count":11},{"id":"2411.00932","title":"LLMs: A Game-Changer for Software Engineers?","created":"2024-11-01","cited_by_count":11},{"id":"2501.11709","title":"Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolution","created":"2025-01-20","cited_by_count":11},{"id":"2503.22625","title":"Challenges and Paths Towards AI for Software Engineering","created":"2025-03-28","cited_by_count":11}],"next_cursor":"100"}