Papers Code Generation

“Code Generation” 태그가 달린 논문 3,075편 · 필터 해제

VibeGuard: A Security Gate Framework for AI-Generated Code

2026-04-01 · Ying Xie arxiv

"Vibe coding," in which developers delegate code generation to AI assistants and accept the output with little manual review, has gained rapid adoption in production settings. On March 31, 2026, Anthropic's Claude Code C…

Code Generation

Embarrassingly Simple Self-Distillation Improves Code Generation

2026-04-01 · Ruixiang Zhang, Richard He Bai, Huangjie Zheng, Navdeep Jaitly 외 arxiv

Can a large language model (LLM) improve at code generation using only its own raw outputs, without a verifier, a teacher model, or reinforcement learning? We answer in the affirmative with simple self-distillation (SSD)…

Reinforcement Learning Code Generation

Ambig-IaC: Multi-level Disambiguation for Interactive Cloud Infrastructure-as-Code Synthesis

2026-04-01 · Zhenning Yang, Kaden Gruizenga, Tongyuan Miao, Patrick Tser Jern Kon 외 arxiv

The scale and complexity of modern cloud infrastructure have made Infrastructure-as-Code (IaC) essential for managing deployments. While large Language models (LLMs) are increasingly being used to generate IaC configurat…

Code Generation

The Hitchhikers Guide to Rubric Quality Understanding and Enrichment

2026-04-01 · Zhengyang Qi, Charles Dickens, Derek Pham, Amanda Dsouza 외 arxiv

Rubrics distill notions of expert quality and measure agent performance. However, the quality of rubrics themselves have not been systematically measured and are often left to downstream performance.We import apparatuses…

Reinforcement Learning Instruction Following Code Generation

WybeCoder: Verified Imperative Code Generation

2026-03-31 · Fabian Gloeckle, Mantas Baksys, Darius Feher, Kunhao Zheng 외 arxiv

Recent progress in large language models (LLMs) has substantially advanced automatic code generation and formal theorem proving, yet software verification has not seen comparable gains. To address this gap, we propose Wy…

Code Generation

APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay

2026-03-31 · Pratyay Banerjee, Masud Moshtaghi, Ankit Chadha arxiv

LLM-based autonomous agents lack persistent procedural memory: they re-derive solutions from scratch even when structurally identical tasks have been solved before. We present APEX-EM, a non-parametric online learning fr…

Code Generation

Self-Improving Code Generation via Semantic Entropy and Behavioral Consensus

2026-03-31 · Huan Zhang, Wei Cheng, Wei Hu arxiv

Improving the code generation capabilities of large language models (LLMs) typically relies on supervised fine-tuning or preference optimization, both of which require costly external resources such as powerful teacher m…

Code Generation

An Empirical Study of Multi-Agent Collaboration for Automated Research

2026-03-31 · Yang Shen, Zhenyi Yi, Ziyi Zhao, Lijun Sun 외 arxiv

As AI agents evolve, the community is rapidly shifting from single Large Language Models (LLMs) to Multi-Agent Systems (MAS) to overcome cognitive bottlenecks in automated research. However, the optimal multi-agent coord…

Code Generation

Think Anywhere in Code Generation

2026-03-31 · Xue Jiang, Tianyu Zhang, Ge Li, Mengyang Liu 외 arxiv

Recent advances in reasoning Large Language Models (LLMs) have primarily relied on upfront thinking, where reasoning occurs before final answer. However, this approach suffers from critical limitations in code generation…

Code Generation

A Taxonomy of Programming Languages for Code Generation

2026-03-31 · Nishat Raihan, Christian Newman, Marcos Zampieri arxiv

The world's 7,000+ languages vary widely in the availability of resources for NLP, motivating efforts to systematically categorize them by their degree of resourcefulness (Joshi et al., 2020). A similar disparity exists …

Code Generation

Human-in-the-Loop Control of Objective Drift in LLM-Assisted Computer Science Education

2026-03-31 · Mark Dranias, Adam Whitley arxiv

Large language models (LLMs) are increasingly embedded in computer science education through AI-assisted programming tools, yet such workflows often exhibit objective drift, in which locally plausible outputs diverge fro…

Code Generation

BACE: LLM-based Code Generation through Bayesian Anchored Co-Evolution of Code and Test Populations

2026-03-30 · Kaushitha Silva, Srinath Perera arxiv

Large Language Models (LLMs) have demonstrated impressive capabilities in code generation. While an interactive feedback loop can improve performance, writing effective tests is a non-trivial task. Early multi-agent fram…

Code Generation

Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs

2026-03-29 · K M Ferdous, Dipayan Banik, Kowshik Chowdhury, Shazibul Islam Shamim arxiv

AI coding agents are increasingly integrated into modern software engineering workflows, actively collaborating with human developers to create pull requests (PRs) in open-source repositories. Although coding agents impr…

Code Generation

PRBench: End-to-end Paper Reproduction in Physics Research

2026-03-29 · Shi Qiu, Junyi Deng, Yiwei Deng, Haoran Dong 외 arxiv

AI agents powered by large language models exhibit strong reasoning and problem-solving capabilities, enabling them to assist scientific research tasks such as formula derivation and code generation. However, whether the…

Code Generation

Needle in the Repo: A Benchmark for Maintainability in AI-Generated Repository Edits

2026-03-29 · Haichao Zhu, Qian Zhang, Jiyuan Wang, Zhaorui Yang 외 arxiv

AI coding agents can now complete complex programming tasks, but existing evaluations largely emphasize behavioral correctness and often overlook maintainability risks such as weak modularity or testability. We present N…

Code Generation

Q-Bridge: Code Translation for Quantum Machine Learning via LLMs

2026-03-29 · Runjia Zeng, Priyabrata Senapati, Ruixiang Tang, Dongfang Liu 외 arxiv

Large language models have recently shown potential in bridging the gap between classical machine learning and quantum machine learning. However, the lack of standardized, high-quality datasets and robust translation fra…

Quantum Machine Learning Code Translation Code Generation

AstraAI: LLMs, Retrieval, and AST-Guided Assistance for HPC Codebases

2026-03-28 · Mahesh Natarajan, Xiaoye Li, Weiqun Zhang arxiv

We present AstraAI, a command-line interface (CLI) coding framework for high-performance computing (HPC) software development. AstraAI operates directly within a Linux terminal and integrates large language models (LLMs)…

Code Generation

SWE-PRBench: Benchmarking AI Code Review Quality Against Pull Request Feedback

2026-03-27 · Deepak Kumar arxiv

We introduce SWE-PRBench, a benchmark of 350 pull requests with human-annotated ground truth for evaluating AI code review quality. Evaluated against an LLM-as-judge framework validated at kappa=0.75, 8 frontier models d…

Code Generation

Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification

2026-03-27 · Zehai He, Wenyi Hong, Zhen Yang, Ziyang Pan 외 arxiv

Recent advances in large language models have improved the capabilities of coding agents, yet systematic evaluation of complex, end-to-end website development remains limited. To address this gap, we introduce Vision2Web…

Code Generation

UCAgent: An End-to-End Agent for Block-Level Functional Verification

2026-03-26 · Junyue Wang, Zhicheng Yao, Yan Pi, Xiaolong Li 외 arxiv

Functional verification remains a critical bottleneck in modern IC development cycles, accounting for approximately 70% of total development time in many projects. However, traditional methods, including constrained-rand…

Code Generation