{"total":83,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"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":"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":"2302.05319","title":"Large Language Models for Code: Security Hardening and Adversarial Testing","created":"2023-02-10","cited_by_count":155,"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":"2401.10491","title":"Knowledge Fusion of Large Language Models","created":"2024-01-19","cited_by_count":115,"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":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47,"area":null},{"id":"2406.06647","title":"How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark","created":"2024-06-10","cited_by_count":43,"area":null},{"id":"2311.08588","title":"CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation","created":"2023-11-14","cited_by_count":39,"area":null},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33,"area":null},{"id":"2407.07565","title":"On Leakage of Code Generation Evaluation Datasets","created":"2024-07-10","cited_by_count":32,"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":"2403.04814","title":"Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks","created":"2024-03-07","cited_by_count":25,"area":null},{"id":"2403.03894","title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","created":"2024-03-06","cited_by_count":23,"area":null},{"id":"2404.03543","title":"CodeEditorBench: Evaluating Code Editing Capability of Large Language Models","created":"2024-04-04","cited_by_count":23,"area":null},{"id":"2405.20574","title":"Open Ko-LLM Leaderboard: Evaluating Large Language Models in Korean with Ko-H5 Benchmark","created":"2024-05-31","cited_by_count":23,"area":null},{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"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":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","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":"2406.12655","title":"Benchmarks and Metrics for Evaluations of Code Generation: A Critical Review","created":"2024-06-18","cited_by_count":20,"area":null},{"id":"2406.16441","title":"UniCoder: Scaling Code Large Language Model via Universal Code","created":"2024-06-24","cited_by_count":18,"area":null},{"id":"2412.09879","title":"On the Limit of Language Models as Planning Formalizers","created":"2024-12-13","cited_by_count":18,"area":null},{"id":"2501.02086","title":"Instruction-Following Pruning for Large Language Models","created":"2025-01-03","cited_by_count":17,"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":"2409.17892","title":"EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2308.12415","title":"Benchmarking Causal Study to Interpret Large Language Models for Source Code","created":"2023-08-23","cited_by_count":14,"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":"2503.07358","title":"RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2410.04715","title":"Selection of LLM Fine-Tuning Data based on Orthogonal Rules","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2404.00399","title":"Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code","created":"2024-03-30","cited_by_count":10,"area":null},{"id":"2311.00317","title":"Data Augmentation for Code Translation with Comparable Corpora and Multiple References","created":"2023-11-01","cited_by_count":9,"area":null},{"id":"2401.03855","title":"PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMs","created":"2024-01-08","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":"2512.15586","title":"Bolmo: Byteifying the Next Generation of Language Models","created":"2025-12-17","cited_by_count":9,"area":null},{"id":"2405.14906","title":"AutoCoder: Enhancing Code Large Language Model with \\textsc{AIEV-Instruct}","created":"2024-05-23","cited_by_count":8,"area":null},{"id":"2408.00994","title":"ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models","created":"2024-08-02","cited_by_count":8,"area":null},{"id":"2312.15692","title":"Instruction Fusion: Advancing Prompt Evolution through Hybridization","created":"2023-12-25","cited_by_count":7,"area":null},{"id":"2401.07870","title":"JumpCoder: Go Beyond Autoregressive Coder via Online Modification","created":"2024-01-15","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":"2410.06577","title":"Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2410.07793","title":"Do Current Language Models Support Code Intelligence for R Programming Language?","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2508.03678","title":"More Than a Score: Probing the Impact of Prompt Specificity on LLM Code Generation","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2603.00539","title":"Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement","created":"2026-02-28","cited_by_count":4,"area":null},{"id":"2605.14967","title":"InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2607.08186","title":"Hidden Decoding at Scale: Latent Computation Scaling for Large Language Models","created":"2026-07-09","cited_by_count":4,"area":null},{"id":"2409.04114","title":"Multi-Programming Language Ensemble for Code Generation in Large Language Model","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2410.18957","title":"Bridge-Coder: Unlocking LLMs' Potential to Overcome Language Gaps in Low-Resource Code","created":"2024-10-24","cited_by_count":3,"area":null},{"id":"2412.08291","title":"Code LLMs: A Taxonomy-based Survey","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2502.18726","title":"Deep-Bench: Deep Learning Benchmark Dataset for Code Generation","created":"2025-02-26","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":"2605.28500","title":"Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2605.30288","title":"MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2403.10575","title":"Exploring Language Model's Code Generation Ability with Auxiliary Functions","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2406.12635","title":"ScenEval: A Benchmark for Scenario-Based Evaluation of Code Generation","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2505.11441","title":"Is Compression Really Linear with Code Intelligence?","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2602.00012","title":"OGD4All: A Framework for Accessible Interaction with Geospatial Open Government Data Based on Large Language Models","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2603.30038","title":"Benchmarking PhD-Level Coding in 3D Geometric Computer Vision","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2407.03387","title":"ConCodeEval: Evaluating Large Language Models for Code Constraints in Domain-Specific Languages","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2407.03941","title":"Narrow Transformer: StarCoder-Based Java-LM For Desktop","created":"2024-07-04","cited_by_count":1,"area":null},{"id":"2505.13126","title":"Iterative Formalization and Planning in Partially Observable Environments","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.13553","title":"Towards Functional Correctness of Large Code Models with Selective Generation","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2507.06138","title":"Coding Triangle: How Does Large Language Model Understand Code?","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2406.14867","title":"Investigating the Transferability of Code Repair for Low-Resource Programming Languages","created":"2024-06-21","cited_by_count":0,"area":null},{"id":"2411.15470","title":"A Preliminary Study of Multilingual Code Language Models for Code Generation Task Using Translated Benchmarks","created":"2024-11-23","cited_by_count":0,"area":null},{"id":"2505.24324","title":"SwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2601.21070","title":"Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.02554","title":"BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.11481","title":"Compiler-Guided Inference-Time Adaptation: Improving GPT-5 Programming Performance in Idris","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.19826","title":"Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.15238","title":"Hydra: Efficient, Correct Code Generation via Checkpoint-and-Rollback Support","created":"2026-05-14","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":"2606.10087","title":"CodeAlchemy: Synthetic Code Rewriting at Scale","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.10722","title":"Continual LLM Upcycling: A Predictor-Gated Bank-Wise Sparsity Training Recipe for Dense-to-Sparse LLMs","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.27401","title":"Recall Before Rerank: Benchmarking Deep Learning Models for Large-Scale Code-to-Code Retrieval","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.18260","title":"FindStatBench: Evaluating Large Language Models on Combinatorial Code Synthesis","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2608.21107","title":"Large Language Models at the Intersection of Software Engineering and Software Security:An Evidence-Centered Structured Survey and Research Agenda","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.30044","title":"Balance of Benchmarks: Semantic Density Reweighting for Task-Conditioned Model Comparison","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.10715","title":"NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}