{"total":21,"rows":[{"id":"2505.05602","title":"HiBayES: A Hierarchical Bayesian Modeling Framework for AI Evaluation Statistics","created":"2025-05-08","cited_by_count":18,"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":"2506.12278","title":"Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposure","created":"2025-06-13","cited_by_count":10,"area":null},{"id":"2510.26130","title":"Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation","created":"2025-10-30","cited_by_count":8,"area":null},{"id":"2511.04355","title":"Where Do LLMs Still Struggle? An In-Depth Analysis of Code Generation Benchmarks","created":"2025-11-06","cited_by_count":5,"area":null},{"id":"2511.00527","title":"A Hierarchical Imprecise Probability Approach to Reliability Assessment of Large Language Models","created":"2025-11-01","cited_by_count":2,"area":null},{"id":"2602.23407","title":"Learning to Generate Secure Code via Token-Level Rewards","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2603.13251","title":"ManiBench: A Benchmark for Testing Visual-Logic Drift and Syntactic Hallucinations in Manim Code Generation","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2608.13566","title":"Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2505.20505","title":"Large Language Models for IT Automation Tasks: Are We There Yet?","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2507.03162","title":"MateInfoUB: A Real-World Benchmark for Testing LLMs in Competitive, Multilingual, and Multimodal Educational Tasks","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2601.22921","title":"Evaluating Large Language Models for Security Bug Report Prediction","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2603.27836","title":"Q-Bridge: Code Translation for Quantum Machine Learning via LLMs","created":"2026-03-29","cited_by_count":1,"area":null},{"id":"2604.02729","title":"IndustryCode: A Benchmark for Industry Code Generation","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.27763","title":"Intent2Tx: Benchmarking LLMs for Translating Natural Language Intents into Ethereum Transactions","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.18073","title":"A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2505.12900","title":"AutoGEEval: A Multimodal and Automated Framework for Geospatial Code Generation on GEE with Large Language Models","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2509.06402","title":"NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2602.00456","title":"Benchmarking Agents in Insurance Underwriting Environments","created":"2026-01-31","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}],"next_cursor":null}