{"total":63,"rows":[{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279,"area":null},{"id":"2502.10517","title":"KernelBench: Can LLMs Write Efficient GPU Kernels?","created":"2025-02-14","cited_by_count":225,"area":null},{"id":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171,"area":null},{"id":"2502.12115","title":"SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?","created":"2025-02-17","cited_by_count":105,"area":null},{"id":"2501.00912","title":"AutoPresent: Designing Structured Visuals from Scratch","created":"2025-01-01","cited_by_count":68,"area":null},{"id":"2605.03546","title":"ProgramBench: Can Language Models Rebuild Programs From Scratch?","created":"2026-05-05","cited_by_count":59,"area":null},{"id":"2411.03292","title":"Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping","created":"2024-11-05","cited_by_count":51,"area":null},{"id":"2506.06251","title":"DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation","created":"2025-06-06","cited_by_count":45,"area":null},{"id":"2502.17521","title":"Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation","created":"2025-02-23","cited_by_count":38,"area":null},{"id":"2412.02883","title":"TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?","created":"2024-12-03","cited_by_count":34,"area":null},{"id":"2601.01426","title":"SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving","created":"2026-01-04","cited_by_count":31,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2502.19400","title":"TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding","created":"2025-02-26","cited_by_count":24,"area":null},{"id":"2602.23166","title":"AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios","created":"2026-02-26","cited_by_count":23,"area":null},{"id":"2503.22424","title":"Issue Localization via LLM-Driven Iterative Code Graph Searching","created":"2025-03-28","cited_by_count":22,"area":null},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2511.06090","title":"SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?","created":"2025-11-08","cited_by_count":21,"area":null},{"id":"2504.12110","title":"Towards LLM Agents for Earth Observation","created":"2025-04-16","cited_by_count":17,"area":null},{"id":"2511.02778","title":"VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation","created":"2025-11-04","cited_by_count":16,"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":"2509.24709","title":"IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2512.03042","title":"PPTArena: A Benchmark for PowerPoint Editing","created":"2025-12-02","cited_by_count":11,"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":"2412.17315","title":"CodeV: Issue Resolving with Visual Data","created":"2024-12-23","cited_by_count":9,"area":null},{"id":"2603.02668","title":"SorryDB: Can AI Provers Complete Real-World Lean Theorems?","created":"2026-03-03","cited_by_count":8,"area":null},{"id":"2501.13699","title":"DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale","created":"2025-01-23","cited_by_count":7,"area":null},{"id":"2502.11525","title":"Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2506.10954","title":"SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks","created":"2025-06-12","cited_by_count":7,"area":null},{"id":"2510.25744","title":"Completion $\\neq$ Collaboration: Scaling Collaborative Effort with Agents","created":"2025-10-29","cited_by_count":6,"area":null},{"id":"2603.01048","title":"RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair","created":"2026-03-01","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2606.15932","title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","created":"2026-06-14","cited_by_count":6,"area":null},{"id":"2606.19830","title":"JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines","created":"2026-06-18","cited_by_count":6,"area":null},{"id":"2602.10471","title":"TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generation","created":"2026-02-11","cited_by_count":5,"area":null},{"id":"2509.03867","title":"Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2509.16187","title":"MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2510.09724","title":"InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2601.12262","title":"Environment-Aware Code Generation: How far are We?","created":"2026-01-18","cited_by_count":4,"area":null},{"id":"2601.13713","title":"SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2601.22859","title":"MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2605.20520","title":"Open-World Evaluations for Measuring Frontier AI Capabilities","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2507.08719","title":"Multilingual Multimodal Software Developer for Code Generation","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2510.03341","title":"OpusAnimation: Code-Based Dynamic Chart Generation","created":"2025-10-02","cited_by_count":3,"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":"2606.00750","title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2606.15300","title":"CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?","created":"2026-06-13","cited_by_count":3,"area":null},{"id":"2509.24148","title":"TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2512.14336","title":"Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure","created":"2025-12-16","cited_by_count":2,"area":null},{"id":"2603.05026","title":"RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2603.13251","title":"ManiBench: A Benchmark for Testing Visual-Logic Drift and Syntactic Hallucinations in Manim Code Generation","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2603.17826","title":"FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2502.01492","title":"Develop AI Agents for System Engineering in Factorio","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2505.20505","title":"Large Language Models for IT Automation Tasks: Are We There Yet?","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2604.00167","title":"A Study on the Impact of Fault localization Granularity for Repository-Scale Code Repair Tasks","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2602.13921","title":"GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.24946","title":"MobileDev-Bench: A Benchmark for Issue Resolution in Mobile Application Development","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.15815","title":"BootstrapAgent: Distilling Repository Setup into Reusable Agent Knowledge","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2608.00084","title":"From Pixels to PCells: A Neurosymbolic Approach to Photonic Component Creation","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.22308","title":"GameReplica: A Benchmark for Black-Box Visual Game Replication by Vision-Language Agents","created":"2026-09-15","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":"2610.04658","title":"RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.05398","title":"MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-Training","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.13022","title":"Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}