{"total":64,"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":"2403.08937","title":"Bugs in Large Language Models Generated Code: An Empirical Study","created":"2024-03-13","cited_by_count":60,"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":"2403.09032","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","created":"2024-03-14","cited_by_count":57,"area":"alignment"},{"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":"2402.07844","title":"Mercury: A Code Efficiency Benchmark for Code Large Language Models","created":"2024-02-12","cited_by_count":35,"area":null},{"id":"2507.23194","title":"Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks","created":"2025-07-31","cited_by_count":32,"area":null},{"id":"2405.15189","title":"EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization","created":"2024-05-24","cited_by_count":30,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2407.14044","title":"ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?","created":"2024-07-19","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":"2507.15887","title":"AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2503.07010","title":"ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation","created":"2025-03-10","cited_by_count":26,"area":"agents"},{"id":"2505.23671","title":"GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents","created":"2025-05-29","cited_by_count":25,"area":"agents"},{"id":"2407.02209","title":"Generative Monoculture in Large Language Models","created":"2024-07-02","cited_by_count":22,"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":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","cited_by_count":18,"area":"alignment"},{"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":"2504.21751","title":"CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation","created":"2025-04-30","cited_by_count":17,"area":null},{"id":"2503.24260","title":"MaintainCoder: Maintainable Code Generation Under Dynamic Requirements","created":"2025-03-31","cited_by_count":14,"area":null},{"id":"2409.09464","title":"Measuring the Influence of Incorrect Code on Test Generation","created":"2024-09-14","cited_by_count":11,"area":null},{"id":"2509.26476","title":"Regression Language Models for Code","created":"2025-09-30","cited_by_count":11,"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":"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":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2509.10099","title":"Generating Energy-Efficient Code via Large-Language Models -- Where are we now?","created":"2025-09-12","cited_by_count":6,"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":"2505.20324","title":"Evaluating the Energy-Efficiency of the Code Generated by LLMs","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2510.26423","title":"Nexus: Execution-Grounded Multi-Agent Test Oracle Synthesis","created":"2025-10-30","cited_by_count":4,"area":"agents"},{"id":"2512.14018","title":"PerfCoder: Large Language Models for Interpretable Code Performance Optimization","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2601.09703","title":"ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation","created":"2026-01-14","cited_by_count":3,"area":"inference"},{"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":"2508.08332","title":"Energy-Aware Code Generation with LLMs: Benchmarking Small vs. Large Language Models for Sustainable AI Programming","created":"2025-08-10","cited_by_count":2,"area":null},{"id":"2605.15222","title":"PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2606.25530","title":"Evaluating LLMs on Real-World Software Performance Optimization","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2601.04540","title":"AdaptEval: A Benchmark for Evaluating Large Language Models on Code Snippet Adaptation","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2603.11935","title":"MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2605.05267","title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2607.01211","title":"Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?","created":"2026-07-01","cited_by_count":1,"area":"agents"},{"id":"2607.27409","title":"SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2506.11081","title":"SAGE:Specification-Aware Grammar Extraction for Automated Test Case Generation with LLMs","created":"2025-06-04","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":"2602.10171","title":"EvoCodeBench: A Human-Performance Benchmark for Self-Evolving LLM-Driven Coding Systems","created":"2026-02-10","cited_by_count":0,"area":"synth"},{"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":"2605.17029","title":"Task Abstention for Large Language Models in Code Generation","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.17978","title":"AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.30394","title":"CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabilities of Large Language Models","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.04023","title":"CodegenBench: Can LLMs Write Efficient Code Across Architectures?","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.10702","title":"Watts and Debts of Agentic Frameworks: An Empirical Study (Registered Report)","created":"2026-06-09","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":"2607.04577","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":"2607.07619","title":"Rethinking Code Performance Benchmarks for LLMs","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2607.07744","title":"PERFOPT-Bench: Evaluating Coding Agents on Software Performance Optimization","created":"2026-07-08","cited_by_count":0,"area":"agents"},{"id":"2607.27271","title":"RLPF: Reinforcement Learning from Performance Feedback for Code Generation","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.06041","title":"LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.10729","title":"Optimal Stopping of Self-Refining Foundation Models","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.12771","title":"Memorization Diagnostics for Code LLMs Should be Scale-Aware","created":"2026-08-13","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":"2609.05232","title":"Substrate-Aware AI Agents: Execution Context as a First-Class Input","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.14839","title":"Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.18052","title":"An Empirical Evaluation of Cost-Efficient Large Language Models on Algorithmic Programming Tasks","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.34427","title":"LLMs as Adaptive Meta-Solvers: Strategy-Diverse RL for Industrial-Scale Optimization","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.02571","title":"Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting","created":"2026-10-01","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}],"next_cursor":null}