{"total":448,"rows":[{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"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":"2406.07496","title":"TextGrad: Automatic \"Differentiation\" via Text","created":"2024-06-11","cited_by_count":273,"area":null},{"id":"2502.10517","title":"KernelBench: Can LLMs Write Efficient GPU Kernels?","created":"2025-02-14","cited_by_count":225,"area":null},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219,"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":"2504.02605","title":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving","created":"2025-04-03","cited_by_count":171,"area":null},{"id":"2406.01304","title":"CodeR: Issue Resolving with Multi-Agent and Task Graphs","created":"2024-06-03","cited_by_count":91,"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":"2501.00912","title":"AutoPresent: Designing Structured Visuals from Scratch","created":"2025-01-01","cited_by_count":68,"area":null},{"id":"2408.03910","title":"CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases","created":"2024-08-07","cited_by_count":65,"area":null},{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65,"area":null},{"id":"2510.20270","title":"ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases","created":"2025-10-23","cited_by_count":65,"area":null},{"id":"2505.21497","title":"Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers","created":"2025-05-27","cited_by_count":63,"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":"2503.06680","title":"FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation","created":"2025-03-09","cited_by_count":58,"area":null},{"id":"2412.01769","title":"Commit0: Library Generation from Scratch","created":"2024-12-02","cited_by_count":52,"area":null},{"id":"2506.12469","title":"Levels of Autonomy for AI Agents","created":"2025-06-14","cited_by_count":48,"area":null},{"id":"2406.11912","title":"AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology","created":"2024-06-16","cited_by_count":46,"area":null},{"id":"2408.05534","title":"Can LLMs Replace Manual Annotation of Software Engineering Artifacts?","created":"2024-08-10","cited_by_count":42,"area":null},{"id":"2502.13681","title":"Repo2Run: Automated Building Executable Environment for Code Repository at Scale","created":"2025-02-19","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":"2407.10701","title":"DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems","created":"2024-07-15","cited_by_count":37,"area":null},{"id":"2408.14354","title":"SWE-bench-java: A GitHub Issue Resolving Benchmark for Java","created":"2024-08-26","cited_by_count":34,"area":null},{"id":"2411.12644","title":"CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval","created":"2024-11-19","cited_by_count":34,"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":"2502.18658","title":"Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support","created":"2025-02-25","cited_by_count":34,"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":"2606.05405","title":"Agents' Last Exam","created":"2026-06-03","cited_by_count":31,"area":null},{"id":"2607.08964","title":"Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading","created":"2026-07-09","cited_by_count":31,"area":null},{"id":"2408.10718","title":"CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?","created":"2024-08-20","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":"2409.04556","title":"How Does Code Pretraining Affect Language Model Task Performance?","created":"2024-09-06","cited_by_count":28,"area":null},{"id":"2505.16901","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","created":"2025-05-22","cited_by_count":27,"area":null},{"id":"2507.15887","title":"AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2510.15863","title":"PolySkill: Learning Generalizable Skills Through Polymorphic Abstraction","created":"2025-10-17","cited_by_count":27,"area":null},{"id":"2502.05368","title":"Otter: Generating Tests from Issues to Validate SWE Patches","created":"2025-02-07","cited_by_count":25,"area":null},{"id":"2409.08775","title":"What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use","created":"2024-09-13","cited_by_count":24,"area":null},{"id":"2412.03578","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","created":"2024-11-18","cited_by_count":24,"area":null},{"id":"2510.02453","title":"How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models","created":"2025-10-02","cited_by_count":24,"area":null},{"id":"2504.16082","title":"MR. Video: \"MapReduce\" is the Principle for Long Video Understanding","created":"2025-04-22","cited_by_count":23,"area":null},{"id":"2604.05550","title":"AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery","created":"2026-04-07","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":"2504.14757","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":"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":"2510.17797","title":"Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics","created":"2025-10-20","cited_by_count":20,"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":"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":"2407.06946","title":"Self-Recognition in Language Models","created":"2024-07-09","cited_by_count":18,"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":"2503.11917","title":"A Framework for Evaluating Emerging Cyberattack Capabilities of AI","created":"2025-03-14","cited_by_count":16,"area":null},{"id":"2512.23075","title":"Trust Region Masking for Long-Horizon LLM Reinforcement Learning","created":"2025-12-28","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":"2604.24658","title":"The Last Human-Written Paper: Agent-Native Research Artifacts","created":"2026-04-27","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":"2503.01811","title":"AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2506.22419","title":"The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements","created":"2025-06-27","cited_by_count":15,"area":null},{"id":"2604.00842","title":"Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants","created":"2026-04-01","cited_by_count":15,"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":"2503.24260","title":"MaintainCoder: Maintainable Code Generation Under Dynamic Requirements","created":"2025-03-31","cited_by_count":14,"area":null},{"id":"2507.16200","title":"RealBench: Benchmarking Verilog Generation Models with Real-World IP Designs","created":"2025-07-22","cited_by_count":14,"area":null},{"id":"2406.12295","title":"Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding","created":"2024-06-18","cited_by_count":13,"area":null},{"id":"2406.18294","title":"Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs","created":"2024-06-26","cited_by_count":13,"area":null},{"id":"2410.09997","title":"Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code","created":"2024-10-13","cited_by_count":13,"area":null},{"id":"2507.13300","title":"AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research","created":"2025-07-17","cited_by_count":13,"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":"2502.15797","title":"OCCULT: Evaluating Large Language Models for Offensive Cyber Operation Capabilities","created":"2025-02-18","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":"2508.02721","title":"Blueprint First, Model Second: A Framework for Deterministic LLM Workflow","created":"2025-08-01","cited_by_count":12,"area":null},{"id":"2511.20766","title":"OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability","created":"2025-11-25","cited_by_count":12,"area":null},{"id":"2607.03935","title":"Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions","created":"2026-07-04","cited_by_count":12,"area":null},{"id":"2410.15625","title":"Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces","created":"2024-10-21","cited_by_count":11,"area":null},{"id":"2412.14764","title":"CodeRepoQA: A Large-scale Benchmark for Software Engineering Question Answering","created":"2024-12-19","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":"2609.00196","title":"WHALE: A Simple Recipe for Joint Harness-Weight Optimization","created":"2026-08-31","cited_by_count":11,"area":null},{"id":"2411.13941","title":"LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues","created":"2024-11-21","cited_by_count":10,"area":null},{"id":"2605.05724","title":"Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes","created":"2026-05-07","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":"2605.13625","title":"How to Interpret Agent Behavior","created":"2026-05-13","cited_by_count":10,"area":null},{"id":"2605.19156","title":"How Far Are We From True Auto-Research?","created":"2026-05-18","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":"2605.29955","title":"Formalizing Mathematics at Scale","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2410.10998","title":"WILT: A Multi-Turn, Memorization-Robust Inductive Logic Benchmark for LLMs","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2412.17315","title":"CodeV: Issue Resolving with Visual Data","created":"2024-12-23","cited_by_count":9,"area":null},{"id":"2506.02049","title":"EvoGit: Decentralized Code Evolution via Git-Based Multi-Agent Collaboration","created":"2025-06-01","cited_by_count":9,"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":"2511.18734","title":"Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion","created":"2025-11-24","cited_by_count":9,"area":null},{"id":"2602.07666","title":"SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned","created":"2026-02-07","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}],"next_cursor":"100"}