{"total":41,"rows":[{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171,"area":null},{"id":"2510.04374","title":"GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks","created":"2025-10-05","cited_by_count":158,"area":null},{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156,"area":null},{"id":"2507.09089","title":"Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity","created":"2025-07-12","cited_by_count":101,"area":null},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"area":null},{"id":"2504.13359","title":"Cost-of-Pass: An Economic Framework for Evaluating Language Models","created":"2025-04-17","cited_by_count":35,"area":null},{"id":"2507.16280","title":"ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry","created":"2025-07-22","cited_by_count":32,"area":null},{"id":"2511.11562","title":"PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning","created":"2025-11-14","cited_by_count":32,"area":null},{"id":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2510.26787","title":"Remote Labor Index: Measuring AI Automation of Remote Work","created":"2025-10-30","cited_by_count":20,"area":null},{"id":"2506.18951","title":"SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications","created":"2025-06-23","cited_by_count":16,"area":null},{"id":"2605.12925","title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","created":"2026-05-13","cited_by_count":15,"area":null},{"id":"2507.09108","title":"SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation","created":"2025-07-12","cited_by_count":12,"area":null},{"id":"2508.14104","title":"You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation","created":"2025-08-17","cited_by_count":12,"area":null},{"id":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10,"area":null},{"id":"2603.04601","title":"Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development","created":"2026-03-04","cited_by_count":9,"area":null},{"id":"2606.30182","title":"MirrorCode: AI can rebuild entire programs from behavior alone","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2507.09866","title":"Turning the Tide: Repository-based Code Reflection","created":"2025-07-14","cited_by_count":5,"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":"2509.16749","title":"Evaluating LLM Generated Detection Rules in Cybersecurity","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2604.24023","title":"ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services","created":"2026-04-27","cited_by_count":4,"area":null},{"id":"2603.22999","title":"PaperVoyager : Building Interactive Web with Visual Language Models","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2604.05912","title":"FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2606.00750","title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2511.20216","title":"CostNav: A Navigation Benchmark for Real-World Economic-Cost Evaluation of Physical AI Agents","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2605.14790","title":"Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2608.11341","title":"Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2503.04828","title":"Beyond Next Word Prediction: Developing Comprehensive Evaluation Frameworks for measuring LLM performance on real world applications","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2503.23053","title":"A Training-free LLM Framework with Interaction between Contextually Related Subtasks in Solving Complex Tasks","created":"2025-03-29","cited_by_count":0,"area":null},{"id":"2512.02567","title":"Feedback Loops and Code Perturbations in LLM-based Software Engineering: A Case Study on a C-to-Rust Translation System","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2601.04920","title":"Conversational AI for Rapid Scientific Prototyping: A Case Study on ESA's ELOPE Competition","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2601.11518","title":"How Long Is a Piece of String? A Brief Empirical Analysis of Tokenizers","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2602.13209","title":"LemonadeBench: Evaluating the Economic Intuition of Large Language Models in Simple Markets","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2605.02661","title":"AcademiClaw: When Students Set Challenges for AI Agents","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.11166","title":"Flaws in the LLM Automation Narrative","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.27283","title":"Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.29560","title":"Which LLM for Which Work? Budgeted Model Allocation under Uncertain Evaluation","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.32662","title":"AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.01306","title":"DAYJOB: A Benchmark for Long-Horizon Professional Work","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04379","title":"AgentPersonaBench: Benchmarking Persona-Driven User Simulation","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.19138","title":"MA-Bench: Measuring Operational Planning in Language Models","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}