{"list":"other","total":52,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2406.12045","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","created":"2024-06-17","cited_by_count":1402},{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"2601.11868","title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","created":"2026-01-17","cited_by_count":585},{"id":"2410.07095","title":"MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering","created":"2024-10-09","cited_by_count":469},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"2409.07429","title":"Agent Workflow Memory","created":"2024-09-11","cited_by_count":383},{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279},{"id":"2006.14799","title":"Evaluation of Text Generation: A Survey","created":"2020-06-26","cited_by_count":277},{"id":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239},{"id":"2206.15000","title":"Grounded Copilot: How Programmers Interact with Code-Generating Models","created":"2022-06-30","cited_by_count":218},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203},{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124},{"id":"2503.15478","title":"SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks","created":"2025-03-19","cited_by_count":118},{"id":"2504.06821","title":"Inducing Programmatic Skills for Agentic Tasks","created":"2025-04-09","cited_by_count":111},{"id":"2302.07080","title":"The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Development","created":"2023-02-14","cited_by_count":96},{"id":"2210.14306","title":"Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming","created":"2022-10-25","cited_by_count":91},{"id":"2303.17125","title":"A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges","created":"2023-03-30","cited_by_count":75},{"id":"2401.12869","title":"TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks","created":"2024-01-23","cited_by_count":75},{"id":"2412.15701","title":"Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration","created":"2024-12-20","cited_by_count":65},{"id":"2510.06552","title":"Flipping the Dialogue: Training and Evaluating User Language Models","created":"2025-10-08","cited_by_count":58},{"id":"1612.05688","title":"A User Simulator for Task-Completion Dialogues","created":"2016-12-17","cited_by_count":57},{"id":"2410.00752","title":"TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark","created":"2024-10-01","cited_by_count":52},{"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":"2304.06597","title":"\"What It Wants Me To Say\": Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models","created":"2023-04-13","cited_by_count":48},{"id":"2202.04903","title":"Investigating Explainability of Generative AI for Code through Scenario-based Design","created":"2022-02-10","cited_by_count":47},{"id":"2511.02208","title":"Training Proactive and Personalized LLM Agents","created":"2025-11-04","cited_by_count":46},{"id":"2403.08604","title":"Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study","created":"2024-03-13","cited_by_count":44},{"id":"2410.04596","title":"Need Help? Designing Proactive AI Assistants for Programming","created":"2024-10-06","cited_by_count":43},{"id":"2507.22358","title":"Magentic-UI: Towards Human-in-the-loop Agentic Systems","created":"2025-07-30","cited_by_count":43},{"id":"2208.06213","title":"What is it like to program with artificial intelligence?","created":"2022-08-12","cited_by_count":39},{"id":"2506.06576","title":"Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce","created":"2025-06-06","cited_by_count":38},{"id":"2305.11248","title":"Investigating and Designing for Trust in AI-powered Code Generation Tools","created":"2023-05-18","cited_by_count":34},{"id":"2404.02806","title":"The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers","created":"2024-04-03","cited_by_count":30},{"id":"2510.19898","title":"BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills","created":"2025-10-22","cited_by_count":30},{"id":"2309.10947","title":"How Do Analysts Understand and Verify AI-Assisted Data Analyses?","created":"2023-09-19","cited_by_count":26},{"id":"2502.09328","title":"Copilot Arena: A Platform for Code LLM Evaluation in the Wild","created":"2025-02-13","cited_by_count":26},{"id":"2506.03011","title":"Coding Agents with Multimodal Browsing are Generalist Problem Solvers","created":"2025-06-03","cited_by_count":25},{"id":"2510.22780","title":"How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations","created":"2025-10-26","cited_by_count":19},{"id":"2501.08774","title":"How Developers Interact with AI: A Taxonomy of Human-AI Collaboration in Software Engineering","created":"2025-01-15","cited_by_count":15},{"id":"2511.04486","title":"EDIT-Bench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits","created":"2025-11-06","cited_by_count":13},{"id":"2503.14724","title":"CodingGenie: A Proactive LLM-Powered Programming Assistant","created":"2025-03-18","cited_by_count":10},{"id":"2512.05356","title":"AI & Human Co-Improvement for Safer Co-Superintelligence","created":"2025-12-05","cited_by_count":8},{"id":"2401.10739","title":"In-IDE Human-AI Experience in the Era of Large Language Models; A Literature Review","created":"2024-01-19","cited_by_count":6},{"id":"2412.20071","title":"Towards Human-AI Synergy in UI Design: Supporting Iterative Generation with LLMs","created":"2024-12-28","cited_by_count":5}],"next_cursor":null}