{"total":232,"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":"2502.13138","title":"AIDE: AI-Driven Exploration in the Space of Code","created":"2025-02-18","cited_by_count":226,"area":null},{"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":"2410.14684","title":"RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph","created":"2024-10-03","cited_by_count":91,"area":null},{"id":"2506.02548","title":"CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale","created":"2025-06-03","cited_by_count":78,"area":null},{"id":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72,"area":null},{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65,"area":null},{"id":"2412.01769","title":"Commit0: Library Generation from Scratch","created":"2024-12-02","cited_by_count":52,"area":null},{"id":"2506.03524","title":"Seed-Coder: Let the Code Model Curate Data for Itself","created":"2025-06-04","cited_by_count":49,"area":null},{"id":"2502.11844","title":"BaxBench: Can LLMs Generate Correct and Secure Backends?","created":"2025-02-17","cited_by_count":41,"area":null},{"id":"2506.09050","title":"ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering","created":"2025-06-10","cited_by_count":39,"area":null},{"id":"2509.24002","title":"MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use","created":"2025-09-28","cited_by_count":39,"area":null},{"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,"area":null},{"id":"2509.14635","title":"SWE-QA: Can Language Models Answer Repository-level Code Questions?","created":"2025-09-18","cited_by_count":38,"area":null},{"id":"2505.24785","title":"EXP-Bench: Can AI Conduct AI Research Experiments?","created":"2025-05-30","cited_by_count":37,"area":null},{"id":"2411.19379","title":"Marconi: Prefix Caching for the Era of Hybrid LLMs","created":"2024-11-28","cited_by_count":31,"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":"2606.05405","title":"Agents' Last Exam","created":"2026-06-03","cited_by_count":31,"area":null},{"id":"2410.06107","title":"Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap","created":"2024-10-08","cited_by_count":30,"area":null},{"id":"2510.19898","title":"BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills","created":"2025-10-22","cited_by_count":30,"area":null},{"id":"2410.18603","title":"AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant","created":"2024-10-24","cited_by_count":27,"area":null},{"id":"2503.08893","title":"EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees","created":"2025-03-11","cited_by_count":27,"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":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2508.14880","title":"MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework","created":"2025-08-20","cited_by_count":22,"area":null},{"id":"2604.25727","title":"Toward Scalable Terminal Task Synthesis via Skill Graphs","created":"2026-04-28","cited_by_count":22,"area":null},{"id":"2606.11926","title":"Toward Generalist Autonomous Research via Hypothesis-Tree Refinement","created":"2026-06-10","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":"2505.07849","title":"SweRank: Software Issue Localization with Code Ranking","created":"2025-05-07","cited_by_count":20,"area":null},{"id":"2506.09003","title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner","created":"2025-06-10","cited_by_count":20,"area":null},{"id":"2510.01003","title":"Improving Code Localization with Repository Memory","created":"2025-10-01","cited_by_count":20,"area":null},{"id":"2411.10478","title":"Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey","created":"2024-11-11","cited_by_count":19,"area":null},{"id":"2502.05714","title":"Proving the Coding Interview: A Benchmark for Formally Verified Code Generation","created":"2025-02-08","cited_by_count":19,"area":null},{"id":"2504.15254","title":"CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation","created":"2025-04-21","cited_by_count":19,"area":null},{"id":"2505.21577","title":"RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving","created":"2025-05-27","cited_by_count":19,"area":null},{"id":"2509.16198","title":"RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation","created":"2025-09-19","cited_by_count":19,"area":null},{"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,"area":null},{"id":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19,"area":null},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19,"area":null},{"id":"2411.11910","title":"AIGS: Generating Science from AI-Powered Automated Falsification","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2601.06123","title":"Latent Space Communication via K-V Cache Alignment","created":"2026-01-04","cited_by_count":17,"area":null},{"id":"2412.14234","title":"Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysis","created":"2024-12-18","cited_by_count":16,"area":null},{"id":"2505.16975","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","created":"2025-05-22","cited_by_count":16,"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":"2604.11641","title":"CodeTracer: Towards Traceable Agent States","created":"2026-04-13","cited_by_count":16,"area":null},{"id":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","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":"2603.07244","title":"PresentBench: A Fine-Grained Rubric-Based Benchmark for Slide Generation","created":"2026-03-07","cited_by_count":14,"area":null},{"id":"2603.13023","title":"daVinci-Env: Open SWE Environment Synthesis at Scale","created":"2026-03-13","cited_by_count":14,"area":null},{"id":"2507.21184","title":"Can Language Models Discover Scaling Laws?","created":"2025-07-27","cited_by_count":13,"area":null},{"id":"2606.05080","title":"AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?","created":"2026-06-03","cited_by_count":13,"area":null},{"id":"2411.13323","title":"Are Large Language Models Memorizing Bug Benchmarks?","created":"2024-11-20","cited_by_count":12,"area":null},{"id":"2504.12397","title":"Activated LoRA: Fine-tuned LLMs for Intrinsics","created":"2025-04-16","cited_by_count":12,"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":"2409.09464","title":"Measuring the Influence of Incorrect Code on Test Generation","created":"2024-09-14","cited_by_count":11,"area":null},{"id":"2601.20882","title":"DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle","created":"2026-01-27","cited_by_count":11,"area":null},{"id":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2504.00018","title":"SandboxEval: Towards Securing Test Environment for Untrusted Code","created":"2025-03-27","cited_by_count":10,"area":null},{"id":"2508.16671","title":"Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verification","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2510.08521","title":"FlowSearch: Advancing deep research with dynamic structured knowledge flow","created":"2025-10-09","cited_by_count":10,"area":null},{"id":"2605.07073","title":"TeamBench: Evaluating Agent Coordination under Enforced Role Separation","created":"2026-05-08","cited_by_count":10,"area":null},{"id":"2605.22535","title":"TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks","created":"2026-05-21","cited_by_count":10,"area":null},{"id":"2605.23204","title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","created":"2026-05-22","cited_by_count":10,"area":null},{"id":"2511.05931","title":"Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement","created":"2025-11-08","cited_by_count":9,"area":null},{"id":"2602.16805","title":"Simple Baselines are Competitive with Code Evolution","created":"2026-02-18","cited_by_count":9,"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":"2605.26302","title":"Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems","created":"2026-05-25","cited_by_count":9,"area":null},{"id":"2606.03461","title":"What Makes Interaction Trajectories Effective for Training Terminal Agents?","created":"2026-06-02","cited_by_count":9,"area":null},{"id":"2606.04455","title":"The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?","created":"2026-06-03","cited_by_count":9,"area":null},{"id":"2502.16662","title":"Saarthi: The First AI Formal Verification Engineer","created":"2025-02-23","cited_by_count":8,"area":null},{"id":"2603.13428","title":"SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution","created":"2026-03-13","cited_by_count":8,"area":null},{"id":"2603.23994","title":"Understanding the Challenges in Iterative Generative Optimization with LLMs","created":"2026-03-25","cited_by_count":8,"area":null},{"id":"2605.09636","title":"PDEAgent-Bench: A Multi-Metric, Multi-Library Benchmark for PDE Solver Generation","created":"2026-05-10","cited_by_count":8,"area":null},{"id":"2605.29559","title":"LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents","created":"2026-05-28","cited_by_count":8,"area":null},{"id":"2606.12344","title":"Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks","created":"2026-06-10","cited_by_count":8,"area":null},{"id":"2608.06352","title":"CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks","created":"2026-08-06","cited_by_count":8,"area":null},{"id":"2609.12541","title":"Agent as Policy for Robotic Manipulation","created":"2026-09-11","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":"2505.10887","title":"InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction","created":"2025-05-16","cited_by_count":7,"area":null},{"id":"2510.26101","title":"QCoder Benchmark: Bridging Language Generation and Quantum Hardware through Simulator-Based Feedback","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2511.16004","title":"InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution","created":"2025-11-20","cited_by_count":7,"area":null},{"id":"2512.20111","title":"ABBEL: Learning Natural-Language Belief States for Memory-Efficient Interaction","created":"2025-12-23","cited_by_count":7,"area":null},{"id":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2506.08762","title":"EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2506.11059","title":"CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2510.14509","title":"E2Edev: Benchmarking Large Language Models in End-to-End Software Development Task","created":"2025-10-16","cited_by_count":6,"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":"2601.13384","title":"From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning","created":"2026-01-19","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":"2604.11716","title":"SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context","created":"2026-04-13","cited_by_count":6,"area":null},{"id":"2605.02572","title":"On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length","created":"2026-05-04","cited_by_count":6,"area":null},{"id":"2503.22444","title":"Scaling Laws in Scientific Discovery with AI and Robot Scientists","created":"2025-03-28","cited_by_count":5,"area":null},{"id":"2505.04670","title":"LLM Code Customization with Visual Results: A Benchmark on TikZ","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2510.20211","title":"Automated Cloud Infrastructure-as-Code Reconciliation with AI Agents","created":"2025-10-23","cited_by_count":5,"area":null},{"id":"2604.06742","title":"Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios","created":"2026-04-08","cited_by_count":5,"area":null},{"id":"2606.00408","title":"Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism","created":"2026-05-29","cited_by_count":5,"area":null},{"id":"2606.04261","title":"Can Generalist Agents Automate Data Curation?","created":"2026-06-02","cited_by_count":5,"area":null}],"next_cursor":"100"}