{"total":39,"rows":[{"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":"2410.24198","title":"SelfCodeAlign: Self-Alignment for Code Generation","created":"2024-10-31","cited_by_count":62,"area":null},{"id":"2501.08200","title":"CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation","created":"2025-01-14","cited_by_count":59,"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":"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":"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":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2410.10209","title":"EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2607.02980","title":"Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling","created":"2026-07-03","cited_by_count":12,"area":null},{"id":"2502.18489","title":"LLM4EFFI: Leveraging Large Language Models to Enhance Code Efficiency and Correctness","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2510.19338","title":"Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning","created":"2025-10-22","cited_by_count":10,"area":null},{"id":"2508.20124","title":"Towards Better Correctness and Efficiency in Code Generation","created":"2025-08-24","cited_by_count":9,"area":null},{"id":"2508.16431","title":"Cetvel: A Unified Benchmark for Evaluating Language Understanding, Generation and Cultural Capacity of LLMs for Turkish","created":"2025-08-22","cited_by_count":8,"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":"2505.11480","title":"SuperCoder: Assembly Program Superoptimization with Large Language Models","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2512.23966","title":"Efficient Context Scaling with LongCat ZigZag Attention","created":"2025-12-30","cited_by_count":6,"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":"2506.18403","title":"The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs","created":"2025-06-23","cited_by_count":5,"area":null},{"id":"2602.04296","title":"ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2602.07080","title":"CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2607.19653","title":"PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2503.06676","title":"Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2505.03818","title":"Program Semantic Inequivalence Game with Large Language Models","created":"2025-05-02","cited_by_count":1,"area":null},{"id":"2602.15449","title":"TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2605.27051","title":"ConVer: Using Contracts and Loop Invariant Synthesis for Scalable Formal Software Verification","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2608.25061","title":"DataKernelBench: Can LLMs Optimize Database Queries on GPUs?","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2412.17395","title":"WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2510.15494","title":"Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.04538","title":"From Model to Breach: Towards Actionable LLM-Generated Vulnerabilities Reporting","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2604.05137","title":"EffiPair: Improving the Efficiency of LLM-generated Code with Differential Execution Feedback","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2605.27981","title":"STAB: Specification-driven Testing for Algorithmic Bottlenecks","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.04577","title":"Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.27271","title":"RLPF: Reinforcement Learning from Performance Feedback for Code Generation","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.15092","title":"WeSCE: A Benchmark for Measuring Security Drift in LLM-Driven Code Editing","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.15931","title":"PLSQLBench: Benchmarking LLM Systems for Executable Procedural Database Programming","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.22220","title":"Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2610.13563","title":"Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue Resolution","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15394","title":"WUSPruner: Second-Moment-Optimal Transforms for Structured Pruning","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.15398","title":"GA-SVD: Generation-aware Singular Value Decomposition for LLM Compression","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}