Papers Code Generation

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

Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding

2026-07-07 · Daniel Maninger, Leon Chemnitz, Jannis Brugger, Tushar Lamba 외 arxiv

Integration of web APIs is a cornerstone of modern software systems, yet writing correct web API invocation code remains challenging due to complex and evolving API specifications. Although LLMs are increasingly used for…

Code Generation

What You See Is What You Get: Observation-Aligned Supervision for Chart-to-Code Generation

2026-07-06 · Tianhao Niu, Qingfu Zhu, Wanxiang Che arxiv

Chart-to-code generation is commonly trained with supervised fine-tuning on reference plotting scripts, implicitly treating the gold code as a fully observable target. We argue that this assumption is often invalid: many…

Code Generation

Beyond the Need for Speed: Energy-Aware Code Generation via Simulation-Guided Reinforcement Learning

2026-07-06 · Saurabhsingh Rajput, Tushar Sharma arxiv

Code models strictly prioritize functional correctness, leaving software energy efficiency as an unoptimized byproduct. Training models to generate energy-efficient code requires reproducible feedback at scale, which phy…

Reinforcement Learning Code Generation

dOPSD: On-Policy Self-Distillation for Diffusion Language Models

2026-07-05 · Phuong Tuan Dat, Qi Li, Xinchao Wang hf

Diffusion large language models (dLLMs) generate text by iteratively denoising a masked sequence, offering a parallel alternative to autoregressive models, but eliciting strong reasoning through post-training remains dif…

Reinforcement Learning Code Generation

Benchmarking API Drift in LLM-Generated Quantum Code Across Successive SDK Versions

2026-07-05 · Mohammad Arif Rasyidi, Syahirul Faiz arxiv

Large language models can generate plausible quantum code, but it is unclear whether they can reliably target the specific software development kit (SDK) version requested by the user. We study this problem as API drift …

Code Generation

Effectiveness of LLM-based Software Diversity for Reliability Improvement -- an Empirical Study

2026-07-03 · Gabriel Almeida, Ilir Gashi, Vladimir Stankovic, João R. Campos arxiv

Software diversity has been extensively studied as a means of reducing the risk of common-mode failures. Classic work showed that the central issue is whether failures of diversely redundant components overlap in ways th…

Code Generation

Builder, Defender, Breaker: The Case Against Removing the Human from the AI-Driven Security Lifecycle

2026-07-03 · Mohamed Chahine Ghanem arxiv

Artificial intelligence has spread across the whole of the security lifecycle. The same family of models now writes application code, hardens it, and probes it for weaknesses, so that a single generative substrate increa…

Code Generation

Beyond Post-Quantization: Native Hash Learning with a Dedicated HASH Token

2026-07-03 · Xinze Liu, Ding Wang, Hengjie Zhu, Dayan Wu arxiv

Efficient large-scale image retrieval requires compact representations that preserve semantic similarity under fast Hamming-space search. Deep hashing is appealing, but most existing CNN- and ViT-based methods still foll…

Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study

2026-07-02 · Achint Mehta arxiv

Agentic coding assistants are increasingly given extra capabilities, such as browser based testing tools and design oriented system prompts, on the assumption that more capability yields better software. This study teste…

Code Generation

DecompRL: Solving Harder Problems by Learning Modular Code Generation

2026-07-02 · Juliette Decugis, Fabian Gloeckle, Francis Bach, Taco Cohen 외 arxiv

How can Large Language Models (LLMs) solve problems they currently cannot? Repeated sampling scales test-time compute but GPU cost grows linearly with attempts, while reinforcement learning (RL) with verifiable rewards i…

Reinforcement Learning Code Generation

PACE: A Proxy for Agentic Capability Evaluation

2026-07-02 · Yueqi Song, Lintang Sutawika, Jiarui Liu, Lindia Tjuatja 외 arxiv

Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure. A single evaluation can cost thousands of dollars and take days to complete. In contrast,…

Code Generation

An Exploratory Study on LLM-Generated Code and Comments in Code Repositories

2026-07-02 · Yongyi Ji, Jiaji Wang, Yi Zhou, Fuxiang Chen 외 arxiv

The use of LLMs in software development has become increasingly widespread on tasks such as code generation and summarization. Reports from large technology companies showed that around 20% to 30% of their code are gener…

Code Generation

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

2026-07-01 · Zijian Zhang, Rizhen Hu, Athanasios Glentis, Dawei Li 외 arxiv

Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how RL adaptation is distributed across transformer layers. Existing approaches typ…

Mathematical Reasoning Reinforcement Learning Code Generation

Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations

2026-07-01 · Mehul Damani, Isha Puri, Idan Shenfeld, Jacob Andreas arxiv

RL with verifiable rewards (RLVR) has emerged as a powerful paradigm for training LMs on tasks with well-defined success metrics, such as code generation and mathematical reasoning. However, current RLVR methods optimize…

Mathematical Reasoning Story Generation Code Generation

A Self-Evolving Agentic System for Automated Generation and Execution of Biological Protocols

2026-06-30 · Yankai Jiang, Weiting Tang, Haoran Sun, Zhenyu Tang 외 arxiv

Autonomous wet-lab experimentation requires more than plausible protocol text: biological intent, quantitative procedures, device constraints and experimental feedback must remain aligned from protocol and SOP design to …

Code Generation

AlgoBench: Benchmarking Algorithmic Adaptation in Code Generation

2026-06-30 · Xinyuan Song, Zekun Cai, Liang Zhao arxiv

High pass rates on established programming benchmarks such as HumanEval and LiveCodeBench do not always show whether a model can reason about algorithms. Many fixed benchmarks eventually become part of the public trainin…

Code Generation

ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL

2026-06-30 · Zijun Xie, Binbin Zheng, Enlei Gong, Jihua Liu 외 arxiv

Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows. Context-management methods make such rollouts feasible by simplifying past interact…

Zero-shot Generalization Code Generation

UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization

2026-06-30 · Yaozhi Zheng, Yilei Jiang, Manyuan Zhang, Yuxuan Wan 외 arxiv

Visual-to-Code generation, which transforms scientific plots, vector graphics, and webpages into executable scripts, demands a level of pixel-precise alignment that standard Multimodal Large Language Models (MLLMs) fail …

Reinforcement Learning Code Generation Code Search

AxDafny: Agentic Verified Code Generation in Dafny

2026-06-30 · Benjamin Breen, Austin Letson, Borja Requena Pozo, Leopoldo Sarra arxiv

We study agentic code generation in Dafny, where a model must generate both executable code and the proof artifacts for verification. We present AxDafny, a verifier-guided repair framework that iteratively generates impl…

Code Generation

CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation

2026-06-30 · Pengcheng Wang, Ziran Liu, Wei Wang, Wei Jiang arxiv

Parameter-Efficient Fine-Tuning (PEFT) commonly adapts pretrained weights through low-rank updates, and recent methods further exploit the singular value decomposition (SVD) of the base weight for initialization or subsp…

parameter-efficient fine-tuning Code Generation