{"total":161,"rows":[{"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":"2407.13168","title":"SciCode: A Research Coding Benchmark Curated by Scientists","created":"2024-07-18","cited_by_count":178,"area":null},{"id":"2411.04905","title":"OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models","created":"2024-11-07","cited_by_count":130,"area":null},{"id":"2503.02240","title":"OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale","created":"2025-03-04","cited_by_count":91,"area":null},{"id":"2504.17192","title":"Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning","created":"2025-04-24","cited_by_count":70,"area":null},{"id":"2502.06193","title":"Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering","created":"2025-02-10","cited_by_count":67,"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":"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":"2407.00379","title":"GraphArena: Evaluating and Exploring Large Language Models on Graph Computation","created":"2024-06-29","cited_by_count":49,"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":"2408.10914","title":"To Code, or Not To Code? Exploring Impact of Code in Pre-training","created":"2024-08-20","cited_by_count":47,"area":null},{"id":"2410.01215","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","created":"2024-10-02","cited_by_count":46,"area":null},{"id":"2412.21199","title":"HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation","created":"2024-12-30","cited_by_count":39,"area":null},{"id":"2507.17773","title":"MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation","created":"2025-07-20","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":"2502.20576","title":"OmniRouter: Budget and Performance Controllable Multi-LLM Routing","created":"2025-02-27","cited_by_count":35,"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":"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":"2407.10627","title":"Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena","created":"2024-07-15","cited_by_count":26,"area":null},{"id":"2407.20143","title":"ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development","created":"2024-07-29","cited_by_count":24,"area":null},{"id":"2502.20082","title":"LongRoPE2: Near-Lossless LLM Context Window Scaling","created":"2025-02-27","cited_by_count":24,"area":null},{"id":"2502.01715","title":"Process-Supervised Reinforcement Learning for Code Generation","created":"2025-02-03","cited_by_count":22,"area":null},{"id":"2502.18297","title":"DeepCircuitX: A Comprehensive Repository-Level Dataset for RTL Code Understanding, Generation, and PPA Analysis","created":"2025-02-25","cited_by_count":21,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2501.04694","title":"EpiCoder: Encompassing Diversity and Complexity in Code Generation","created":"2025-01-08","cited_by_count":20,"area":null},{"id":"2410.20527","title":"CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming","created":"2024-10-27","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":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","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":"2410.01353","title":"Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2409.06446","title":"HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data","created":"2024-09-10","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":"2505.18091","title":"Data Mixing Can Induce Phase Transitions in Knowledge Acquisition","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2509.11252","title":"Exploring the Potential of Diffusion Large Language Models in Code Generation","created":"2025-09-14","cited_by_count":16,"area":null},{"id":"2503.22688","title":"CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation","created":"2025-03-05","cited_by_count":15,"area":null},{"id":"2408.02487","title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2502.19852","title":"ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments","created":"2025-02-27","cited_by_count":14,"area":null},{"id":"2601.15892","title":"Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model","created":"2026-01-22","cited_by_count":13,"area":null},{"id":"2506.03483","title":"APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training","created":"2025-06-04","cited_by_count":12,"area":null},{"id":"2412.15184","title":"Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning","created":"2024-12-19","cited_by_count":11,"area":null},{"id":"2510.12803","title":"AutoCode: LLMs as Problem Setters for Competitive Programming","created":"2025-09-29","cited_by_count":11,"area":null},{"id":"2407.01638","title":"LASSI: An LLM-based Automated Self-Correcting Pipeline for Translating Parallel Scientific Codes","created":"2024-06-30","cited_by_count":10,"area":null},{"id":"2407.11470","title":"Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2409.15186","title":"Location is Key: Leveraging Large Language Model for Functional Bug Localization in Verilog","created":"2024-09-23","cited_by_count":10,"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":"2503.01506","title":"SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity","created":"2025-03-03","cited_by_count":10,"area":null},{"id":"2407.12022","title":"ITERTL: An Iterative Framework for Fine-tuning LLMs for RTL Code Generation","created":"2024-06-28","cited_by_count":9,"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":"2412.15304","title":"TinyLLM: A Framework for Training and Deploying Language Models at the Edge Computers","created":"2024-12-19","cited_by_count":9,"area":null},{"id":"2504.01986","title":"TuRTLe: A Unified Evaluation of LLMs for RTL Generation","created":"2025-03-31","cited_by_count":9,"area":null},{"id":"2407.08642","title":"Towards Building Specialized Generalist AI with System 1 and System 2 Fusion","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2408.14158","title":"Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning","created":"2024-08-26","cited_by_count":8,"area":null},{"id":"2412.15178","title":"HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages","created":"2024-12-19","cited_by_count":8,"area":null},{"id":"2502.18505","title":"Comprehensive Analysis of Transparency and Accessibility of ChatGPT, DeepSeek, And other SoTA Large Language Models","created":"2025-02-21","cited_by_count":8,"area":null},{"id":"2506.02073","title":"Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2506.14111","title":"Essential-Web v1.0: 24T tokens of organized web data","created":"2025-06-17","cited_by_count":8,"area":null},{"id":"2508.00033","title":"GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries","created":"2025-07-30","cited_by_count":8,"area":null},{"id":"2512.05356","title":"AI & Human Co-Improvement for Safer Co-Superintelligence","created":"2025-12-05","cited_by_count":8,"area":null},{"id":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2503.02844","title":"Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2504.18050","title":"Validating Network Protocol Parsers with Traceable RFC Document Interpretation","created":"2025-04-25","cited_by_count":7,"area":null},{"id":"2505.10443","title":"Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?","created":"2025-05-15","cited_by_count":7,"area":null},{"id":"2508.05242","title":"CodeBoost: Boosting Code LLMs by Squeezing Knowledge from Code Snippets with RL","created":"2025-08-07","cited_by_count":7,"area":null},{"id":"2601.22760","title":"AscendCraft: Automatic Ascend NPU Kernel Generation via DSL-Guided Transcompilation","created":"2026-01-30","cited_by_count":7,"area":null},{"id":"2408.15079","title":"BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline","created":"2024-08-27","cited_by_count":6,"area":null},{"id":"2410.21236","title":"Flaming-hot Initiation with Regular Execution Sampling for Large Language Models","created":"2024-10-28","cited_by_count":6,"area":null},{"id":"2501.07857","title":"Hierarchical Repository-Level Code Summarization for Business Applications Using Local LLMs","created":"2025-01-14","cited_by_count":6,"area":null},{"id":"2503.20840","title":"CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervision","created":"2025-03-26","cited_by_count":6,"area":null},{"id":"2508.07932","title":"\\(X\\)-evolve: Solution space evolution powered by large language models","created":"2025-08-11","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":"2410.02115","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2410.15154","title":"MCCoder: Streamlining Motion Control with LLM-Assisted Code Generation and Rigorous Verification","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2503.05507","title":"Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?","created":"2025-03-07","cited_by_count":5,"area":null},{"id":"2504.13515","title":"Large Language Models for Validating Network Protocol Parsers","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2505.23932","title":"SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2506.01074","title":"How Programming Concepts and Neurons Are Shared in Code Language Models","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2509.04078","title":"RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models","created":"2025-09-04","cited_by_count":5,"area":null},{"id":"2509.21072","title":"Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution","created":"2025-09-25","cited_by_count":5,"area":null},{"id":"2407.12220","title":"Questionable practices in machine learning","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2408.13745","title":"DOCE: Finding the Sweet Spot for Execution-Based Code Generation","created":"2024-08-25","cited_by_count":4,"area":null},{"id":"2410.03234","title":"Showing LLM-Generated Code Selectively Based on Confidence of LLMs","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2410.18251","title":"Context-Augmented Code Generation Using Programming Knowledge Graphs","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2502.06556","title":"MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2503.11617","title":"ASMA-Tune: Unlocking LLMs' Assembly Code Comprehension via Structural-Semantic Instruction Tuning","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2503.11858","title":"OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2505.15356","title":"NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2507.12284","title":"MERA Code: A Unified Framework for Evaluating Code Generation Across Tasks","created":"2025-07-16","cited_by_count":4,"area":null},{"id":"2508.08171","title":"PyVeritas: On Verifying Python via LLM-Based Transpilation and Bounded Model Checking for C","created":"2025-08-11","cited_by_count":4,"area":null},{"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":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2411.00006","title":"Personality-Guided Code Generation Using Large Language Models","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2412.08063","title":"ContextModule: Improving Code Completion via Repository-level Contextual Information","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2503.22776","title":"Post-Incorporating Code Structural Knowledge into Pretrained Models via ICL for Code Translation","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2504.07483","title":"Program Skeletons for Automated Program Translation","created":"2025-04-10","cited_by_count":3,"area":null},{"id":"2505.02184","title":"Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes","created":"2025-05-04","cited_by_count":3,"area":null},{"id":"2506.04038","title":"Generating Automotive Code: Large Language Models for Software Development and Verification in Safety-Critical Systems","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2506.22776","title":"Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation","created":"2025-06-28","cited_by_count":3,"area":null},{"id":"2507.05281","title":"CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks","created":"2025-07-04","cited_by_count":3,"area":null},{"id":"2507.10898","title":"MalCodeAI: Autonomous Vulnerability Detection and Remediation via Language Agnostic Code Reasoning","created":"2025-07-15","cited_by_count":3,"area":null},{"id":"2601.04252","title":"Sphinx: Benchmarking and Modeling for LLM-Driven Pull Request Review","created":"2026-01-06","cited_by_count":3,"area":null}],"next_cursor":"100"}