Copertina

ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jiang, Juyong, Shen, Jiasi, Kim, Sunghun, Yoo, Kang Min, Kim, Jeonghoon, Kim, Sungju
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Machine Learning Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Survey on Large Language Models for Code Generation
di: Jiang, Juyong, et al.
Pubblicazione: (2024)

WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning
di: Jiang, Juyong, et al.
Pubblicazione: (2026)

DesignCoder: Hierarchy-Aware and Self-Correcting UI Code Generation with Large Language Models
di: Chen, Yunnong, et al.
Pubblicazione: (2025)

TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models
di: Park, Chansung, et al.
Pubblicazione: (2026)

OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification
di: Li, Shangyu, et al.
Pubblicazione: (2025)

Self-planning Code Generation with Large Language Models
di: Jiang, Xue, et al.
Pubblicazione: (2023)

ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation
di: He, Minghua, et al.
Pubblicazione: (2025)

CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora
di: Li, Shangyu, et al.
Pubblicazione: (2026)

Ensuring Functional Correctness of Large Code Models with Selective Generation
di: Jeong, Jaewoo, et al.
Pubblicazione: (2025)

How Effective are Large Language Models in Generating Software Specifications?
di: Xie, Danning, et al.
Pubblicazione: (2023)

Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap
di: Kim, Naryeong, et al.
Pubblicazione: (2026)

ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models
di: Han, Hojae, et al.
Pubblicazione: (2024)

StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
di: Dou, Shihan, et al.
Pubblicazione: (2024)

CoderEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models
di: Yu, Hao, et al.
Pubblicazione: (2023)

COBOL-Coder: Domain-Adapted Large Language Models for COBOL Code Generation and Translation
di: Dau, Anh T. V., et al.
Pubblicazione: (2026)

CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation
di: Pan, Ruwei, et al.
Pubblicazione: (2025)

When LLMs Meet API Documentation: Can Retrieval Augmentation Aid Code Generation Just as It Helps Developers?
di: Chen, Jingyi, et al.
Pubblicazione: (2025)

ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models
di: Yang, Chengran, et al.
Pubblicazione: (2024)

Where Is Self-admitted Code Generated by Large Language Models on GitHub?
di: Yu, Xiao, et al.
Pubblicazione: (2024)

PlayCoder: Making LLM-Generated GUI Code Playable
di: Peng, Zhiyuan, et al.
Pubblicazione: (2026)

InstructCoder: Instruction Tuning Large Language Models for Code Editing
di: Li, Kaixin, et al.
Pubblicazione: (2023)

PerfCoder: Large Language Models for Interpretable Code Performance Optimization
di: Yang, Jiuding, et al.
Pubblicazione: (2025)

GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model
di: Liu, Wei, et al.
Pubblicazione: (2024)

Lachesis: Predicting LLM Inference Accuracy using Structural Properties of Reasoning Paths
di: Kim, Naryeong, et al.
Pubblicazione: (2024)

Perceptual Self-Reflection in Agentic Physics Simulation Code Generation
di: Shende, Prashant, et al.
Pubblicazione: (2026)

Large Language Model Guided Self-Debugging Code Generation
di: Adnan, Muntasir, et al.
Pubblicazione: (2025)

EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuning
di: Huang, Dong, et al.
Pubblicazione: (2024)

AutoCoder: Enhancing Code Large Language Model with \textsc{AIEV-Instruct}
di: Lei, Bin, et al.
Pubblicazione: (2024)

Self-collaboration Code Generation via ChatGPT
di: Dong, Yihong, et al.
Pubblicazione: (2023)

WybeCoder: Verified Imperative Code Generation
di: Gloeckle, Fabian, et al.
Pubblicazione: (2026)

VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning
di: Le, Cuong Chi, et al.
Pubblicazione: (2024)

SparseCoder: Advancing Source Code Analysis with Sparse Attention and Learned Token Pruning
di: Yang, Xueqi, et al.
Pubblicazione: (2023)

R2Code: A Self-Reflective LLM Framework for Requirements-to-Code Traceability
di: Wang, Yifei, et al.
Pubblicazione: (2026)

Identifying Bug Inducing Commits by Combining Fault Localisation and Code Change Histories
di: An, Gabin, et al.
Pubblicazione: (2025)

A Low-Code Methodology for Developing AI Kiosks: a Case Study with the DIZEST Platform
di: Moon, SunMin, et al.
Pubblicazione: (2025)

InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct
di: Wu, Yutong, et al.
Pubblicazione: (2024)

GLLM: Self-Corrective G-Code Generation using Large Language Models with User Feedback
di: Abdelaal, Mohamed, et al.
Pubblicazione: (2025)

StructCoder: Structure-Aware Transformer for Code Generation
di: Tipirneni, Sindhu, et al.
Pubblicazione: (2022)

ZeroCoder: Can LLMs Improve Code Generation Without Ground-Truth Supervision?
di: Fan, Lishui, et al.
Pubblicazione: (2026)

AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation
di: Zhu, Yueheng, et al.
Pubblicazione: (2025)