{"total":87,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2407.01489","title":"Agentless: Demystifying LLM-based Software Engineering Agents","created":"2024-07-01","cited_by_count":421,"area":"agents"},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"area":null},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238,"area":null},{"id":"2411.07763","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","created":"2024-11-12","cited_by_count":232,"area":null},{"id":"2502.10517","title":"KernelBench: Can LLMs Write Efficient GPU Kernels?","created":"2025-02-14","cited_by_count":225,"area":null},{"id":"2311.17311","title":"Universal Self-Consistency for Large Language Model Generation","created":"2023-11-29","cited_by_count":203,"area":"lr"},{"id":"2410.03859","title":"SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?","created":"2024-10-04","cited_by_count":203,"area":null},{"id":"2407.13168","title":"SciCode: A Research Coding Benchmark Curated by Scientists","created":"2024-07-18","cited_by_count":178,"area":null},{"id":"2505.13259","title":"From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery","created":"2025-05-19","cited_by_count":93,"area":null},{"id":"2408.09667","title":"BLADE: Benchmarking Language Model Agents for Data-Driven Science","created":"2024-08-19","cited_by_count":77,"area":"agents"},{"id":"2310.17807","title":"Clover: Closed-Loop Verifiable Code Generation","created":"2023-10-26","cited_by_count":67,"area":null},{"id":"2212.10561","title":"Parsel: Algorithmic Reasoning with Language Models by Composing Decompositions","created":"2022-12-20","cited_by_count":64,"area":"lr"},{"id":"2402.02037","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","created":"2024-02-03","cited_by_count":64,"area":null},{"id":"2404.14662","title":"NExT: Teaching Large Language Models to Reason about Code Execution","created":"2024-04-23","cited_by_count":63,"area":"lr"},{"id":"2410.07331","title":"DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models","created":"2024-10-09","cited_by_count":58,"area":"agents"},{"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,"area":"agents"},{"id":"2306.17842","title":"SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs","created":"2023-06-30","cited_by_count":55,"area":null},{"id":"2309.14345","title":"Bias Testing and Mitigation in LLM-based Code Generation","created":"2023-09-03","cited_by_count":53,"area":null},{"id":"2310.19791","title":"LILO: Learning Interpretable Libraries by Compressing and Documenting Code","created":"2023-10-30","cited_by_count":49,"area":null},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47,"area":null},{"id":"2506.23719","title":"DABstep: Data Agent Benchmark for Multi-step Reasoning","created":"2025-06-30","cited_by_count":46,"area":"lr"},{"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,"area":null},{"id":"2410.04739","title":"TableRAG: Million-Token Table Understanding with Language Models","created":"2024-10-07","cited_by_count":41,"area":null},{"id":"2505.07782","title":"MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering","created":"2025-05-12","cited_by_count":41,"area":"agents"},{"id":"2310.10628","title":"Data Contamination Through the Lens of Time","created":"2023-10-16","cited_by_count":40,"area":null},{"id":"2403.19114","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","created":"2024-03-28","cited_by_count":40,"area":null},{"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,"area":"agents"},{"id":"2506.06541","title":"KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes","created":"2025-06-06","cited_by_count":33,"area":null},{"id":"2407.06423","title":"InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation","created":"2024-07-08","cited_by_count":32,"area":"agents"},{"id":"2409.01392","title":"ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems","created":"2024-09-02","cited_by_count":30,"area":"agents"},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","cited_by_count":27,"area":null},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27,"area":null},{"id":"2405.11430","title":"MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation","created":"2024-05-19","cited_by_count":26,"area":null},{"id":"2403.04814","title":"Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks","created":"2024-03-07","cited_by_count":25,"area":null},{"id":"2505.23671","title":"GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents","created":"2025-05-29","cited_by_count":25,"area":"agents"},{"id":"2309.04369","title":"Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluation","created":"2023-09-08","cited_by_count":24,"area":null},{"id":"2402.08699","title":"Unsupervised Evaluation of Code LLMs with Round-Trip Correctness","created":"2024-02-13","cited_by_count":23,"area":null},{"id":"2404.00566","title":"CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks","created":"2024-03-31","cited_by_count":23,"area":null},{"id":"2512.04324","title":"DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle","created":"2025-12-03","cited_by_count":23,"area":"agents"},{"id":"2406.06464","title":"Transforming Wearable Data into Personal Health Insights using Large Language Model Agents","created":"2024-06-10","cited_by_count":19,"area":"lr"},{"id":"2510.05318","title":"BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions","created":"2025-10-06","cited_by_count":19,"area":null},{"id":"2403.05307","title":"Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents","created":"2024-03-08","cited_by_count":17,"area":"agents"},{"id":"2503.23145","title":"CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis","created":"2025-03-29","cited_by_count":16,"area":"lr"},{"id":"2509.23988","title":"LLM/Agent-as-Data-Analyst: A Survey","created":"2025-09-28","cited_by_count":16,"area":"agents"},{"id":"2510.01285","title":"LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science","created":"2025-09-30","cited_by_count":15,"area":"agents"},{"id":"2601.16344","title":"DSGym: A Holistic Framework for Evaluating and Training Data Science Agents","created":"2026-01-22","cited_by_count":15,"area":"agents"},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2506.19724","title":"From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking","created":"2025-06-24","cited_by_count":12,"area":"agents"},{"id":"2505.11604","title":"Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation","created":"2025-05-16","cited_by_count":11,"area":null},{"id":"2510.23045","title":"A Survey of AI Scientists","created":"2025-10-27","cited_by_count":11,"area":null},{"id":"2509.24405","title":"Multilingual Text-to-SQL: Benchmarking the Limits of Language Models with Collaborative Language Agents","created":"2025-09-29","cited_by_count":8,"area":"agents"},{"id":"2405.01580","title":"On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2507.22462","title":"IFEvalCode: Controlled Code Generation","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2312.13876","title":"Capture the Flag: Uncovering Data Insights with Large Language Models","created":"2023-12-21","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2506.08800","title":"Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents","created":"2025-06-10","cited_by_count":4,"area":"agents"},{"id":"2510.09595","title":"LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2602.24288","title":"DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science","created":"2026-02-27","cited_by_count":4,"area":null},{"id":"2409.13551","title":"Contextualized Data-Wrangling Code Generation in Computational Notebooks","created":"2024-09-20","cited_by_count":3,"area":null},{"id":"2511.22884","title":"InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents","created":"2025-11-28","cited_by_count":3,"area":"agents"},{"id":"2605.08687","title":"PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2308.05317","title":"Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning","created":"2023-08-10","cited_by_count":2,"area":null},{"id":"2504.21043","title":"CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2602.00012","title":"OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Based on Large Language Models","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2604.00491","title":"Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2409.03402","title":"Game On: Towards Language Models as RL Experimenters","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2412.12852","title":"Selective Shot Learning for Code Explanation","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2501.01014","title":"MDSF: Context-Aware Multi-Dimensional Data Storytelling Framework based on Large language Model","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2505.12185","title":"EVALOOOP: A Self-Consistency-Centered Framework for Assessing Large Language Model Robustness in Programming","created":"2025-05-18","cited_by_count":1,"area":"lr"},{"id":"2507.11742","title":"CRABS: A syntactic-semantic pincer strategy for bounding LLM interpretation of Python notebooks","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2507.23336","title":"DSBC : Data Science task Benchmarking with Context engineering","created":"2025-07-31","cited_by_count":1,"area":"agents"},{"id":"2602.07195","title":"Automated Modernization of Machine Learning Engineering Notebooks for Reproducibility","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.12483","title":"Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuel","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2605.21027","title":"Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs","created":"2026-05-20","cited_by_count":1,"area":"agents"},{"id":"2608.10366","title":"DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2403.11585","title":"Linguacodus: A Synergistic Framework for Transformative Code Generation in Machine Learning Pipelines","created":"2024-03-18","cited_by_count":0,"area":null},{"id":"2509.23979","title":"ByteSized32Refactored: Towards an Extensible Interactive Text Games Corpus for LLM World Modeling and Evaluation","created":"2025-09-28","cited_by_count":0,"area":"wm"},{"id":"2511.11933","title":"InData: Towards Secure Multi-Step, Tool-Based Data Analysis","created":"2025-11-14","cited_by_count":0,"area":"agents"},{"id":"2512.18456","title":"SoK: Understanding (New) Security Issues Across AI4Code Use Cases","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2512.23713","title":"PyBangla at BLP-2025 Task 2: Enhancing Bangla-to-Python Code Generation with Iterative Self-Correction and Multilingual Agents","created":"2025-11-27","cited_by_count":0,"area":"agents"},{"id":"2604.16314","title":"Software Self-Extension with SelfEvolve: an Agentic Architecture for Runtime Code Generation","created":"2026-02-06","cited_by_count":0,"area":"agents"},{"id":"2606.12620","title":"HybridCodeAuthorship: A Benchmark Dataset for Line-Level Code Authorship Detection","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.23877","title":"JupOtter: Cell-Level Bug Detection in Jupyter Notebooks","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2609.30749","title":"ORCA: Evaluating LLMs on Data Science Code Translation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.04927","title":"Assembling Insights for Agentic Machine Learning Engineering Systems","created":"2026-10-04","cited_by_count":0,"area":"agents"}],"next_cursor":null}