{"total":178,"rows":[{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417,"area":null},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532,"area":null},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2401.03065","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","created":"2024-01-05","cited_by_count":300,"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":"2311.04934","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","created":"2023-11-07","cited_by_count":268,"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":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"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":"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":"2405.04324","title":"Granite Code Models: A Family of Open Foundation Models for Code Intelligence","created":"2024-05-07","cited_by_count":117,"area":null},{"id":"2306.14893","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","created":"2023-06-26","cited_by_count":112,"area":null},{"id":"2410.16179","title":"MagicPIG: LSH Sampling for Efficient LLM Generation","created":"2024-10-21","cited_by_count":111,"area":null},{"id":"2404.00599","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-03-31","cited_by_count":72,"area":null},{"id":"2405.19856","title":"DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-05-30","cited_by_count":72,"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":"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":"2402.02037","title":"EffiBench: Benchmarking the Efficiency of Automatically Generated Code","created":"2024-02-03","cited_by_count":64,"area":null},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62,"area":null},{"id":"2406.01422","title":"Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration","created":"2024-06-03","cited_by_count":58,"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":"2309.14345","title":"Bias Testing and Mitigation in LLM-based Code Generation","created":"2023-09-03","cited_by_count":53,"area":null},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53,"area":null},{"id":"2503.02130","title":"Forgetting Transformer: Softmax Attention with a Forget Gate","created":"2025-03-03","cited_by_count":53,"area":null},{"id":"2406.11612","title":"Long Code Arena: a Set of Benchmarks for Long-Context Code Models","created":"2024-06-17","cited_by_count":50,"area":null},{"id":"2403.16792","title":"Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback","created":"2024-03-25","cited_by_count":46,"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":"2403.08604","title":"Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study","created":"2024-03-13","cited_by_count":44,"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":"2405.19782","title":"Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion","created":"2024-05-30","cited_by_count":40,"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":"2510.00446","title":"LongCodeZip: Compress Long Context for Code Language Models","created":"2025-10-01","cited_by_count":39,"area":null},{"id":"2505.07897","title":"LongCodeBench: Evaluating Coding LLMs at 1M Context Windows","created":"2025-05-12","cited_by_count":37,"area":null},{"id":"2412.14363","title":"ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals","created":"2024-12-18","cited_by_count":36,"area":null},{"id":"2503.14443","title":"EnvBench: A Benchmark for Automated Environment Setup","created":"2025-03-18","cited_by_count":36,"area":null},{"id":"2406.06025","title":"RepoQA: Evaluating Long Context Code Understanding","created":"2024-06-10","cited_by_count":35,"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":"2404.06480","title":"Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks","created":"2024-04-09","cited_by_count":32,"area":null},{"id":"2411.00136","title":"LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators","created":"2024-10-31","cited_by_count":32,"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":"2406.14712","title":"Qiskit HumanEval: An Evaluation Benchmark For Quantum Code Generative Models","created":"2024-06-20","cited_by_count":30,"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":"2403.16443","title":"CodeS: Natural Language to Code Repository via Multi-Layer Sketch","created":"2024-03-25","cited_by_count":28,"area":null},{"id":"2407.00402","title":"Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP","created":"2024-06-29","cited_by_count":27,"area":null},{"id":"2505.13004","title":"EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code","created":"2025-05-19","cited_by_count":27,"area":null},{"id":"2405.11430","title":"MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation","created":"2024-05-19","cited_by_count":26,"area":null},{"id":"2405.17378","title":"RTL-Repo: A Benchmark for Evaluating LLMs on Large-Scale RTL Design Projects","created":"2024-05-27","cited_by_count":26,"area":null},{"id":"2308.16458","title":"BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models","created":"2023-08-31","cited_by_count":25,"area":null},{"id":"2403.04814","title":"Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks","created":"2024-03-07","cited_by_count":25,"area":null},{"id":"2406.11927","title":"On the Impacts of Contexts on Repository-Level Code Generation","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2401.07004","title":"Extending LLMs' Context Window with 100 Samples","created":"2024-01-13","cited_by_count":21,"area":null},{"id":"2407.09726","title":"On Mitigating Code LLM Hallucinations with API Documentation","created":"2024-07-13","cited_by_count":21,"area":null},{"id":"2410.21157","title":"M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluation","created":"2024-10-28","cited_by_count":21,"area":null},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2412.11990","title":"ExecRepoBench: Multi-level Executable Code Completion Evaluation","created":"2024-12-16","cited_by_count":20,"area":null},{"id":"2505.07849","title":"SweRank: Software Issue Localization with Code Ranking","created":"2025-05-07","cited_by_count":20,"area":null},{"id":"2405.20092","title":"Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation","created":"2024-05-30","cited_by_count":19,"area":null},{"id":"2407.06249","title":"CodeUpdateArena: Benchmarking Knowledge Editing on API Updates","created":"2024-07-08","cited_by_count":19,"area":null},{"id":"2411.09909","title":"AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference","created":"2024-11-15","cited_by_count":19,"area":null},{"id":"2502.19166","title":"CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation","created":"2025-02-26","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":"2410.01353","title":"Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2503.06689","title":"DependEval: Benchmarking LLMs for Repository Dependency Understanding","created":"2025-03-09","cited_by_count":17,"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":"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":"2403.06095","title":"RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion","created":"2024-03-10","cited_by_count":15,"area":null},{"id":"2408.02509","title":"Black-Box Adversarial Attacks on LLM-Based Code Completion","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2503.24260","title":"MaintainCoder: Maintainable Code Generation Under Dynamic Requirements","created":"2025-03-31","cited_by_count":14,"area":null},{"id":"2508.18106","title":"A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code","created":"2025-08-25","cited_by_count":14,"area":null},{"id":"2404.07940","title":"InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models","created":"2024-03-11","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":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13,"area":null},{"id":"2402.13583","title":"LongWanjuan: Towards Systematic Measurement for Long Text Quality","created":"2024-02-21","cited_by_count":11,"area":null},{"id":"2407.13739","title":"Scaling Granite Code Models to 128K Context","created":"2024-07-18","cited_by_count":11,"area":null},{"id":"2503.13299","title":"A Survey on Transformer Context Extension: Approaches and Evaluation","created":"2025-03-17","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":"2408.03519","title":"RepoMasterEval: Evaluating Code Completion via Real-World Repositories","created":"2024-08-07","cited_by_count":10,"area":null},{"id":"2504.08734","title":"Towards an Understanding of Context Utilization in Code Intelligence","created":"2025-04-11","cited_by_count":10,"area":null},{"id":"2601.06789","title":"MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences","created":"2026-01-11","cited_by_count":10,"area":null},{"id":"2409.00921","title":"Statically Contextualizing Large Language Models with Typed Holes","created":"2024-09-02","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":"2406.03283","title":"CATCODER: Repository-Level Code Generation with Relevant Code and Type Context","created":"2024-06-05","cited_by_count":8,"area":null},{"id":"2502.08806","title":"CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification","created":"2025-02-12","cited_by_count":8,"area":null},{"id":"2502.16704","title":"Code Summarization Beyond Function Level","created":"2025-02-23","cited_by_count":8,"area":null},{"id":"2505.19959","title":"MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models","created":"2025-05-26","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":"2505.18148","title":"Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Find","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2509.14221","title":"GEM-Bench: A Benchmark for Ad-Injected Response Generation within Generative Engine Marketing","created":"2025-09-17","cited_by_count":7,"area":null},{"id":"2509.15038","title":"Value-Guided KV Compression for LLMs via Approximated CUR Decomposition","created":"2025-09-18","cited_by_count":7,"area":null},{"id":"2405.01580","title":"On the Limitations of Embedding Based Methods for Measuring Functional Correctness for Code Generation","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2411.05830","title":"GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models","created":"2024-11-05","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":"2411.04156","title":"Crystal: Illuminating LLM Abilities on Language and Code","created":"2024-11-06","cited_by_count":5,"area":null},{"id":"2505.04406","title":"YABLoCo: Yet Another Benchmark for Long Context Code Generation","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2507.20888","title":"Enhancing Project-Specific Code Completion by Inferring Internal API Information","created":"2025-07-28","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":"2601.13240","title":"KOCO-BENCH: Can Large Language Models Leverage Domain Knowledge in Software Development?","created":"2026-01-19","cited_by_count":5,"area":null}],"next_cursor":"100"}