{"list":"other","total":57,"rows":[{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2602.12670","title":"SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks","created":"2026-02-13","cited_by_count":315},{"id":"2404.05427","title":"AutoCodeRover: Autonomous Program Improvement","created":"2024-04-08","cited_by_count":278},{"id":"2406.01297","title":"When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs","created":"2024-06-03","cited_by_count":240},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238},{"id":"2306.09896","title":"Is Self-Repair a Silver Bullet for Code Generation?","created":"2023-06-16","cited_by_count":197},{"id":"2307.07221","title":"Software Testing with Large Language Models: Survey, Landscape, and Vision","created":"2023-07-14","cited_by_count":166},{"id":"2209.11515","title":"Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction","created":"2022-09-23","cited_by_count":111},{"id":"2305.04087","title":"Self-Edit: Fault-Aware Code Editor for Code Generation","created":"2023-05-06","cited_by_count":111},{"id":"2401.08500","title":"Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering","created":"2024-01-16","cited_by_count":103},{"id":"2502.14382","title":"S*: Test Time Scaling for Code Generation","created":"2025-02-20","cited_by_count":98},{"id":"2110.06773","title":"Leveraging Automated Unit Tests for Unsupervised Code Translation","created":"2021-10-13","cited_by_count":82},{"id":"2404.14646","title":"Exploring and Unleashing the Power of Large Language Models in Automated Code Translation","created":"2024-04-23","cited_by_count":57},{"id":"2405.17503","title":"Code Repair with LLMs gives an Exploration-Exploitation Tradeoff","created":"2024-05-26","cited_by_count":51},{"id":"2404.10100","title":"LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation","created":"2024-04-15","cited_by_count":49},{"id":"2405.01466","title":"A Systematic Literature Review on Large Language Models for Automated Program Repair","created":"2024-05-02","cited_by_count":37},{"id":"2412.02883","title":"TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?","created":"2024-12-03","cited_by_count":34},{"id":"2605.27366","title":"MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation","created":"2026-05-26","cited_by_count":27},{"id":"2506.23749","title":"A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications","created":"2025-06-30","cited_by_count":25},{"id":"2407.20898","title":"ThinkRepair: Self-Directed Automated Program Repair","created":"2024-07-30","cited_by_count":23},{"id":"2506.09003","title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner","created":"2025-06-10","cited_by_count":20},{"id":"2403.01971","title":"ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs","created":"2024-03-04","cited_by_count":19},{"id":"2311.09868","title":"INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair","created":"2023-11-16","cited_by_count":18},{"id":"2605.07358","title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","created":"2026-05-08","cited_by_count":18},{"id":"2408.11296","title":"RePair: Automated Program Repair with Process-based Feedback","created":"2024-08-21","cited_by_count":16},{"id":"2305.13592","title":"Understanding Programs by Exploiting (Fuzzing) Test Cases","created":"2023-05-23","cited_by_count":13},{"id":"2507.17542","title":"AssertFlip: Reproducing Bugs via Inversion of LLM-Generated Passing Tests","created":"2025-07-23","cited_by_count":11},{"id":"2602.03712","title":"SWE-Refactor: A Repository-Level Benchmark for Real-World LLM-Based Code Refactoring","created":"2026-02-03","cited_by_count":11},{"id":"2508.06365","title":"Heterogeneous Prompting and Execution Feedback for SWE Issue Test Generation and Selection","created":"2025-08-08","cited_by_count":10},{"id":"2606.16769","title":"Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents","created":"2026-06-15","cited_by_count":10},{"id":"2312.05657","title":"PerfRL: A Small Language Model Framework for Efficient Code Optimization","created":"2023-12-09","cited_by_count":8},{"id":"2606.11435","title":"Agent Skill Evaluation and Evolution: Frameworks and Benchmarks","created":"2026-06-09","cited_by_count":8},{"id":"2409.19894","title":"TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment","created":"2024-09-30","cited_by_count":7},{"id":"2507.22853","title":"Repair-R1: Better Test Before Repair","created":"2025-07-30","cited_by_count":6},{"id":"2505.09027","title":"Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation","created":"2025-05-13","cited_by_count":5},{"id":"2307.00593","title":"Isolating Compiler Bugs by Generating Effective Witness Programs with Large Language Models","created":"2023-07-02","cited_by_count":4},{"id":"2312.04687","title":"LLM4TDD: Best Practices for Test Driven Development Using Large Language Models","created":"2023-12-07","cited_by_count":4},{"id":"2409.16739","title":"Automated Unit Test Refactoring","created":"2024-09-25","cited_by_count":4},{"id":"2602.03557","title":"Scaling Test-Driven Code Generation from Functions to Classes: An Empirical Study","created":"2026-02-03","cited_by_count":4},{"id":"2405.10849","title":"Generative AI for Test Driven Development: Preliminary Results","created":"2024-05-17","cited_by_count":3},{"id":"2602.15761","title":"A Differential Fuzzing-Based Evaluation of Functional Equivalence in LLM-Generated Code Refactorings","created":"2026-02-17","cited_by_count":3},{"id":"2608.10538","title":"SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models","created":"2026-08-11","cited_by_count":3},{"id":"2508.01357","title":"HyClone: Bridging LLM Understanding and Dynamic Execution for Semantic Code Clone Detection","created":"2025-08-02","cited_by_count":2},{"id":"2509.24148","title":"TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation","created":"2025-09-29","cited_by_count":2},{"id":"2607.26244","title":"Do Code Language Models Follow Tests? Paired Interventions on Program Behavior","created":"2026-07-28","cited_by_count":2},{"id":"2608.09740","title":"Security Tests as Executable Specifications for LLM Code Generation: Benefits, Trade-offs, and Coverage Limits","created":"2026-08-10","cited_by_count":2},{"id":"2510.23350","title":"Validating Formal Specifications with LLM-generated Test Cases","created":"2025-10-27","cited_by_count":1},{"id":"2602.02964","title":"Testing Framework Migration with Large Language Models","created":"2026-02-03","cited_by_count":1},{"id":"2607.09065","title":"Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skills","created":"2026-07-10","cited_by_count":1},{"id":"2607.17286","title":"IssueExec: A Test-Driven Approach for Localizing Software Engineering Issues","created":"2026-07-19","cited_by_count":1},{"id":"2607.25032","title":"Authoring Agent Skills: A Software-Engineering Approach","created":"2026-07-27","cited_by_count":1},{"id":"2608.14128","title":"DepWareTrans: Dependency-Aware Incremental Repository Migration across Co-executable Languages","created":"2026-08-14","cited_by_count":1}],"next_cursor":null}