{"total":57,"rows":[{"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":"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":"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":"2407.02883","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","created":"2024-07-03","cited_by_count":60,"area":null},{"id":"2404.09486","title":"MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems","created":"2024-04-15","cited_by_count":40,"area":"mllm"},{"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":"2506.09443","title":"LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge","created":"2025-06-11","cited_by_count":37,"area":"safety"},{"id":"2408.13001","title":"CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution","created":"2024-08-23","cited_by_count":31,"area":"lr"},{"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":"2410.24117","title":"AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validation","created":"2024-10-31","cited_by_count":28,"area":null},{"id":"2412.17744","title":"RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation","created":"2024-12-23","cited_by_count":23,"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":"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":"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":"2406.16441","title":"UniCoder: Scaling Code Large Language Model via Universal Code","created":"2024-06-24","cited_by_count":18,"area":null},{"id":"2406.07411","title":"VersiCode: Towards Version-controllable Code Generation","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2408.03573","title":"AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling","created":"2024-08-07","cited_by_count":17,"area":null},{"id":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","created":"2025-10-10","cited_by_count":15,"area":"agents"},{"id":"2312.10321","title":"LLM-SQL-Solver: Can LLMs Determine SQL Equivalence?","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2504.15424","title":"LLM-Assisted Translation of Legacy FORTRAN Codes to C++: A Cross-Platform Study","created":"2025-04-21","cited_by_count":7,"area":null},{"id":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2606.11864","title":"CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding","created":"2026-06-10","cited_by_count":7,"area":"agents"},{"id":"2505.03418","title":"Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey","created":"2025-05-06","cited_by_count":6,"area":"lr"},{"id":"2510.03588","title":"REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement","created":"2025-10-04","cited_by_count":6,"area":"agents"},{"id":"2507.09866","title":"Turning the Tide: Repository-based Code Reflection","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2507.22462","title":"IFEvalCode: Controlled Code Generation","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2408.14515","title":"A Joint Learning Model with Variational Interaction for Multilingual Program Translation","created":"2024-08-25","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":"2507.11083","title":"Function-to-Style Guidance of LLMs for Code Translation","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2501.16050","title":"Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation","created":"2025-01-27","cited_by_count":3,"area":null},{"id":"2503.07693","title":"Fully Autonomous Programming using Iterative Multi-Agent Debugging with Large Language Models","created":"2025-03-10","cited_by_count":3,"area":"agents"},{"id":"2503.21889","title":"StarFlow: Generating Structured Workflow Outputs From Sketch Images","created":"2025-03-27","cited_by_count":3,"area":"mllm"},{"id":"2505.12925","title":"CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2510.10956","title":"Project-Level C-to-Rust Translation via Pointer Knowledge Graphs","created":"2025-10-13","cited_by_count":3,"area":null},{"id":"2512.21332","title":"C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling","created":"2025-12-24","cited_by_count":3,"area":null},{"id":"2601.20615","title":"DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning","created":"2026-01-28","cited_by_count":3,"area":"rag"},{"id":"2504.09474","title":"MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions","created":"2025-04-13","cited_by_count":2,"area":null},{"id":"2604.07341","title":"ReCodeAgent: A Multi-agent Workflow for Language-Agnostic Translation and Validation of Large-Scale Repositories","created":"2026-04-08","cited_by_count":2,"area":"agents"},{"id":"2604.25960","title":"Large Language Models for Multilingual Code Intelligence: A Survey","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2607.18859","title":"PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2501.00363","title":"SPDZCoder: Combining Expert Knowledge with LLMs for Generating Privacy-Computing Code","created":"2024-12-31","cited_by_count":1,"area":null},{"id":"2507.03958","title":"A Comparative Study of Specialized LLMs as Dense Retrievers","created":"2025-07-05","cited_by_count":1,"area":"mllm"},{"id":"2510.16809","title":"When Many-Shot Prompting Fails: An Empirical Study of LLM Code Translation","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2512.22628","title":"M2G-Eval: Enhancing and Evaluating Multi-granularity Multilingual Code Generation","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2607.19407","title":"ITPEval: Benchmarking Formal Translation Across Interactive Theorem Provers","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2507.16037","title":"A Pilot Study on LLM-Based Agentic Translation from Android to iOS: Pitfalls and Insights","created":"2025-07-21","cited_by_count":0,"area":"agents"},{"id":"2510.09898","title":"Learning Bug Context for PyTorch-to-JAX Translation with LLMs","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.15004","title":"Automated Snippet-Alignment Data Augmentation for Code Translation","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2512.18456","title":"SoK: Understanding (New) Security Issues Across AI4Code Use Cases","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2601.16661","title":"Revisiting the Role of Natural Language Code Comments in Code Translation","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2605.13229","title":"Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization","created":"2026-05-13","cited_by_count":0,"area":"alignment"},{"id":"2605.29054","title":"Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2606.17683","title":"Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.18642","title":"Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.13854","title":"Bootstrapping Niche Multilingual Code Translation via Reinforcement Learning with Execution-Based Verifiable Supervision","created":"2026-08-14","cited_by_count":0,"area":"alignment"},{"id":"2609.30749","title":"ORCA: Evaluating LLMs on Data Science Code Translation","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}