Papers Code Generation
“Code Generation” 태그가 달린 논문 3,075편 · 필터 해제
VHDLSuite: Unified Pipeline for LLM VHDL Generation with Data Synthesis and Evaluation
Large Language Models (LLM) have shown impressive capabilities in Register Transfer Level (RTL) code generation, particularly for Verilog. However, evaluating their performance with other Hardware Description Languages (…
Code GenerationAn LLM System for Autonomous Variational Quantum Circuit Design
The design of high performing quantum circuits remains largely dependent on human expertise. We introduce an autonomous agentic framework that employs large language models (LLMs) to conduct iterative quantum circuit des…
Quantum Machine LearningImage ClassificationCode GenerationToward Instructions-as-Code: Understanding the Impact of Instruction Files on Agentic Pull Requests
AI-agents (e.g., GitHub Copilot) collaborate as teammates in different software engineering tasks, including code generation proposed through pull requests (Agentic-PRs). For better agent efficiency, developers create in…
Code GenerationDrugBench: Evaluating AI Control Protocols for Medication Harm Mitigation
Large Language Models have the potential to expand and improve the access to clinical information by enabling new ways of interacting with medical knowledge in natural language. However, their deployment in medical quest…
Code GenerationGrammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decoding (GCD) has been widely adopted to improv…
Code GenerationAgreement in Representation Space for Open-Ended Self-Consistency
Self-consistency improves LLM reasoning by sampling multiple outputs and selecting the most consistent answer, but existing formulations largely rely on exact matching and therefore remain limited to tasks with categoric…
Mathematical ReasoningText SummarizationCode GenerationBreaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-Token Prediction (MTP) offers a natural so…
Reinforcement LearningMathematical ReasoningCode GenerationShopping Reasoning Bench: An Expert-Authored Benchmark for Multi-Turn Conversational Shopping Assistants
Conversational shopping assistants now serve hundreds of millions of customers, yet no existing benchmark jointly evaluates the open-ended multi-turn reasoning, domain expertise, and criterion-level quality that real sho…
Question AnsweringCode GenerationToken Complexity Theory for AI-Augmented Computing
AI-augmented computing delegates natural language queries, code generation requests, and other open-ended tasks to a cluster of AI models that processes queries and generates responses. This paradigm introduces a resourc…
Natural Language QueriesCode GenerationOpenRTLSet: A Fully Open-Source Dataset for Large Language Model-based Verilog Module Design
OpenRTLSet introduces the largest fully open-source dataset for hardware design, offering over 131,000 diverse Verilog code samples to the research community and industry. Our dataset uniquely combines Verilog code from …
Code Generation3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis
Most recent 3D reconstruction and editing systems operate on implicit and explicit representations such as NeRF, point clouds, or meshes. While these representations enable high-fidelity rendering, they are fundamentally…
3D ReconstructionCode GenerationPoint CloudsA Constrained Natural-Language Interface for Variational Multi-Physics Finite Element Simulations in FEniCS
Large language models can reduce the manual effort required to set up finite element simulations, but they introduce reliability risks when generated solver code lies on the critical path. We present a constrained natura…
Code GenerationMind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?
The deployment of Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade productivity software is largely untested. We argue that Office autom…
Code GenerationClaude Code-Driving Scenario Mining for the Argoverse 2 Challenge
We present our submission to the CVPR 2026 Argoverse 2 Scenario Mining Challenge. Our system uses a four-stage pipeline: (1) autonomous code generation via a Claude Code agent powered by GLM~5.1, (2) iterative training s…
Code GenerationMulti-task LLMs for Bug Classification: Efficient Inference with Auxiliary Decoding Heads
The rapid adoption of LLM-powered code generation has dramatically accelerated software development, yet effective verification methods remain severely underdeveloped. Existing bug localization techniques are either proh…
Code GenerationPriFT: Prior-Support Guided Supervised Fine-Tuning
Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation and often serves as the initialization stage for reinforcement learning (RL), but it can show weaker generalization than RL. A key limi…
Reinforcement LearningMathematical ReasoningQuestion AnsweringCode GenerationCode Is More Than Text: Uncertainty Estimation for Code Generation
Large language models (LLMs) are increasingly deployed as code generators, where silently wrong programs pose real safety and reliability risks. Reliable uncertainty estimation (UE) is essential for selective prediction,…
Code GenerationFASE: Fast Adaptive Semantic Entropy for Code Quality
Multi-agent code generation offers a promising paradigm for autonomous software development by simulating the human software engineering lifecycle. However, system reliability remains hindered by LLM hallucinations and e…
Code GenerationSelf-Evolving Scientific Agent Designs Physically Reasoned White-Box Fluid Control
While neural networks excel in autonomous control, their black-box nature makes control decisions difficult to interpret and diagnose in dynamic fluids. Here, we show how self-evolving scientific agents can design explic…
Reinforcement LearningPhysical SimulationsCode GenerationAsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decoding
Block-wise semi-autoregressive decoding is the standard inference paradigm for diffusion large language models (DLMs), but it imposes a strict dependency between blocks: the next block cannot begin until the current bloc…
Mathematical ReasoningCode Generation