Papers Code Generation
“Code Generation” 태그가 달린 논문 3,075편 · 필터 해제
CodeComp: Structural KV Cache Compression for Agentic Coding
Agentic code tasks such as fault localization and patch generation require processing long codebases under tight memory constraints, where the Key-Value (KV) cache becomes the primary inference bottleneck. Existing compr…
Code GenerationEnhancing LLM Problem Solving via Tutor-Student Multi-Agent Interaction
Human cognitive development is shaped not only by individual effort but by structured social interaction, where role-based exchanges such as those between a tutor and a learner, enable solutions that neither could achiev…
Code GenerationDeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation
Large Language Models (LLMs) for code generation can replicate insecure patterns from their training data. To mitigate this, a common strategy for security hardening is to fine-tune models using supervision derived from …
Code GenerationUIPress: Bringing Optical Token Compression to UI-to-Code Generation
UI-to-Code generation requires vision-language models (VLMs) to produce thousands of tokens of structured HTML/CSS from a single screenshot, making visual token efficiency critical. Existing compression methods either se…
Code GenerationFrom Intent to AI Pipelines: A Controlled Agentic Framework for Non-AI Expert Scientists
Artificial Intelligence (AI) pipelines have become integral to modern research, supporting fields such as Medical Sciences, Agriculture, and Social Sciences, and enabling large-scale data analysis, predictive modeling, a…
Code GenerationPioneer Agent: Continual Improvement of Small Language Models in Production
Small language models are attractive for production deployment due to their low cost, fast inference, and ease of specialization. However, adapting them to a specific task remains a challenging engineering loop, driven n…
Intent ClassificationCode GenerationSLM Finetuning for Natural Language to Domain Specific Code Generation in Production
Many applications today use large language models for code generation; however, production systems have strict latency requirements that can be difficult to meet with large models. Small language models with a few billio…
Code GenerationAn Imperfect Verifier is Good Enough: Learning with Noisy Rewards
Reinforcement Learning with Verifiable Rewards (RLVR) has become a prominent method for post-training Large Language Models (LLMs). However, verifiers are rarely error-free; even deterministic checks can be inaccurate, a…
Reinforcement LearningCode GenerationBeyond the Autoregressive Horizon: A Comprehensive Survey of Diffusion Models, World Modelling, and State Space Models for Code
Autoregressive (AR) language models have driven significant progress in automated software engineering, enabling powerful code generation and assistance systems. However, the next-token prediction paradigm introduces str…
Code GenerationImperfect Visual Verification for Code Edition : A Case Study on TikZ
LLMs have significantly advanced code generation, enabling the synthesis of functional programs. While recent systems achieve strong performance on many coding benchmarks, tasks involving programs such as TikZ that gener…
Code GenerationSkip-Connected Policy Optimization for Implicit Advantage
Group Relative Policy Optimization (GRPO) has proven effective in RLVR by using outcome-based rewards. While fine-grained dense rewards can theoretically improve performance, we reveal that under practical sampling budge…
Code GenerationAI-Driven Research for Databases
As the complexity of modern workloads and hardware increasingly outpaces human research and engineering capacity, existing methods for database performance optimization struggle to keep pace. To address this gap, a new c…
Code GenerationOmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward
The paradigm of programmable diagram generation is evolving rapidly, playing a crucial role in structured visualization. However, most existing studies are confined to a narrow range of task formulations and language sup…
Reinforcement LearningCode GenerationVision-Guided Iterative Refinement for Frontend Code Generation
Code generation with large language models often relies on multi-stage human-in-the-loop refinement, which is effective but very costly - particularly in domains such as frontend web development where the solution qualit…
parameter-efficient fine-tuningCode GenerationDeep Researcher Agent: An Autonomous Framework for 24/7 Deep Learning Experimentation with Zero-Cost Monitoring
We present \textbf{Deep Researcher Agent}, an open-source framework that enables large language model (LLM) agents to autonomously conduct deep learning experiments around the clock. Unlike existing AI research assistant…
Code GenerationArch: An AI-Native Hardware Description Language for Register-Transfer Clocked Hardware Design
We present Arch (AI-native Register-transfer Clocked Hardware), a hardware description language for micro-architecture specification and AI-assisted code generation. Arch provides first-class constructs for pipelines, FS…
Code GenerationInference-Time Code Selection via Symbolic Equivalence Partitioning
Sampling multiple candidate programs at inference time is an effective way to improve LLM code generation. However, its benefit depends on reliably selecting a correct solution from the generated pool. We observe that th…
Code GenerationSampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo
We introduce a principled probabilistic framework for reward-guided decoding in large language models, addressing the limitations of standard decoding methods that optimize token-level likelihood rather than sequence-lev…
Mathematical ReasoningReinforcement LearningCode GenerationFLeX: Fourier-based Low-rank EXpansion for multilingual transfer
Cross-lingual code generation is critical in enterprise environments where multiple programming languages coexist. However, fine-tuning large language models (LLMs) individually for each language is computationally prohi…
parameter-efficient fine-tuningCross-Lingual TransferCode GenerationCompiled AI: Deterministic Code Generation for LLM-Based Workflow Automation
We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which workflows execute deterministically without further model invocation. This paradi…
Code Generation