{"list":"other","total":74,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2108.09293","title":"Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions","created":"2021-08-20","cited_by_count":431},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"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":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278},{"id":"2302.06590","title":"The Impact of AI on Developer Productivity: Evidence from GitHub Copilot","created":"2023-02-13","cited_by_count":274},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238},{"id":"2002.04087","title":"Human-Centered Artificial Intelligence: Reliable, Safe & Trustworthy","created":"2020-02-10","cited_by_count":183},{"id":"2404.11584","title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","created":"2024-04-17","cited_by_count":168},{"id":"2502.08235","title":"The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks","created":"2025-02-12","cited_by_count":152},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135},{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126},{"id":"2102.09692","title":"To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making","created":"2021-02-19","cited_by_count":118},{"id":"1808.09588","title":"Mapping Language to Code in Programmatic Context","created":"2018-08-29","cited_by_count":104},{"id":"2401.04259","title":"MARG: Multi-Agent Review Generation for Scientific Papers","created":"2024-01-08","cited_by_count":104},{"id":"2507.02825","title":"Establishing Best Practices for Building Rigorous Agentic Benchmarks","created":"2025-07-03","cited_by_count":102},{"id":"2411.07781","title":"RedCode: Risky Code Execution and Generation Benchmark for Code Agents","created":"2024-11-12","cited_by_count":90},{"id":"2302.02187","title":"Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations","created":"2023-02-04","cited_by_count":83},{"id":"2401.15897","title":"Red-Teaming for Generative AI: Silver Bullet or Security Theater?","created":"2024-01-29","cited_by_count":83},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79},{"id":"2411.02305","title":"CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments","created":"2024-11-04","cited_by_count":71},{"id":"2405.00623","title":"\"I'm Not Sure, But...\": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust","created":"2024-05-01","cited_by_count":67},{"id":"2406.10279","title":"We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs","created":"2024-06-12","cited_by_count":65},{"id":"2407.10956","title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?","created":"2024-07-15","cited_by_count":56},{"id":"2302.04012","title":"CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models","created":"2023-02-08","cited_by_count":55},{"id":"2405.11804","title":"(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts","created":"2024-05-20","cited_by_count":49},{"id":"2503.15223","title":"Are \"Solved Issues\" in SWE-bench Really Solved Correctly? An Empirical Study","created":"2025-03-19","cited_by_count":49},{"id":"2506.12286","title":"The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason","created":"2025-06-14","cited_by_count":49},{"id":"2109.05067","title":"The Flaws of Policies Requiring Human Oversight of Government Algorithms","created":"2021-09-10","cited_by_count":44},{"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":"2405.02213","title":"Automatic Programming: Large Language Models and Beyond","created":"2024-05-03","cited_by_count":36},{"id":"2405.11514","title":"Towards Translating Real-World Code with LLMs: A Study of Translating to Rust","created":"2024-05-19","cited_by_count":35},{"id":"2305.11248","title":"Investigating and Designing for Trust in AI-powered Code Generation Tools","created":"2023-05-18","cited_by_count":34},{"id":"2405.00253","title":"CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification","created":"2024-04-30","cited_by_count":34},{"id":"2205.05057","title":"Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theory","created":"2022-05-10","cited_by_count":32},{"id":"2308.09932","title":"Unveiling Memorization in Code Models","created":"2023-08-19","cited_by_count":30},{"id":"2312.11658","title":"Traces of Memorisation in Large Language Models for Code","created":"2023-12-18","cited_by_count":29},{"id":"2404.04059","title":"On the Quest for Effectiveness in Human Oversight: Interdisciplinary Perspectives","created":"2024-04-05","cited_by_count":28},{"id":"2511.15080","title":"Anthropic Economic Index report: Uneven geographic and enterprise AI adoption","created":"2025-11-19","cited_by_count":26},{"id":"2201.11569","title":"Human Interpretation of Saliency-based Explanation Over Text","created":"2022-01-27","cited_by_count":25},{"id":"2502.05368","title":"Otter: Generating Tests from Issues to Validate SWE Patches","created":"2025-02-07","cited_by_count":25},{"id":"2202.04092","title":"Machine Explanations and Human Understanding","created":"2022-02-08","cited_by_count":20},{"id":"2211.06753","title":"Seamful XAI: Operationalizing Seamful Design in Explainable AI","created":"2022-11-12","cited_by_count":20},{"id":"2410.12944","title":"How much does AI impact development speed? An enterprise-based randomized controlled trial","created":"2024-10-16","cited_by_count":20},{"id":"2512.14012","title":"Professional Software Developers Don't Vibe, They Control: AI Agent Use for Coding in 2025","created":"2025-12-16","cited_by_count":20},{"id":"2502.19166","title":"CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation","created":"2025-02-26","cited_by_count":19},{"id":"2506.02040","title":"Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem","created":"2025-05-31","cited_by_count":19},{"id":"2510.25779","title":"Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets","created":"2025-10-27","cited_by_count":19},{"id":"2112.01298","title":"Meaningful human control: actionable properties for AI system development","created":"2021-11-25","cited_by_count":18},{"id":"2308.04375","title":"Understanding the Effect of Counterfactual Explanations on Trust and Reliance on AI for Human-AI Collaborative Clinical Decision Making","created":"2023-08-08","cited_by_count":18},{"id":"2305.04699","title":"Runtime Monitoring of Dynamic Fairness Properties","created":"2023-05-08","cited_by_count":17},{"id":"2311.14713","title":"The Rise of the AI Co-Pilot: Lessons for Design from Aviation and Beyond","created":"2023-11-16","cited_by_count":15},{"id":"2205.05306","title":"The Conflict Between Explainable and Accountable Decision-Making Algorithms","created":"2022-05-11","cited_by_count":13},{"id":"2405.05581","title":"One vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations","created":"2024-05-09","cited_by_count":13},{"id":"2507.15241","title":"FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents","created":"2025-07-21","cited_by_count":12},{"id":"2305.14331","title":"What Else Do I Need to Know? The Effect of Background Information on Users' Reliance on QA Systems","created":"2023-05-23","cited_by_count":9},{"id":"2505.00875","title":"Thoughts without Thinking: Reconsidering the Explanatory Value of Chain-of-Thought Reasoning in LLMs through Agentic Pipelines","created":"2025-05-01","cited_by_count":7},{"id":"2601.21920","title":"From Future of Work to Future of Workers: Addressing Asymptomatic AI Harms for Dignified Human-AI Interaction","created":"2026-01-29","cited_by_count":6},{"id":"2509.14528","title":"Why Johnny Can't Use Agents: Industry Aspirations vs. User Realities with AI Agents","created":"2025-09-18","cited_by_count":5},{"id":"2310.07802","title":"An Information Bottleneck Characterization of the Understanding-Workload Tradeoff","created":"2023-10-11","cited_by_count":3},{"id":"2507.03536","title":"ACE: Automated Technical Debt Remediation with Validated Large Language Model Refactorings","created":"2025-07-04","cited_by_count":2}],"next_cursor":null}