Papers Code Generation
“Code Generation” 태그가 달린 논문 3,075편 · 필터 해제
DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
Large Language Model (LLM) agents can automate data-science workflows, but many rigorous statistical methods implemented in R remain underused because LLMs struggle with statistical knowledge and tool retrieval. Existing…
Code GenerationSEA-TS: Self-Evolving Agent for Autonomous Code Generation of Time Series Forecasting Algorithms
Accurate time series forecasting underpins decision-making in many domains, yetconventional ML development often faces data scarcity, distribution shift, anddiminishing returns from manual iteration. We propose Self-Evol…
Time Series ForecastingCode GenerationFree Lunch for Pass@$k$? Low Cost Diverse Sampling for Diffusion Language Models
Diverse outputs in text generation are necessary for effective exploration in complex reasoning tasks, such as code generation and mathematical problem solving. Such Pass@$k$ problems benefit from distinct candidates cov…
Code GenerationText GenerationBeyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes
Diffusion Language Models (DLMs) promise highly parallel text generation, yet their practical inference speed is often bottlenecked by suboptimal decoding schedulers. Standard approaches rely on 'scattered acceptance'-co…
Mathematical ReasoningCode GenerationText GenerationAutonomous Algorithm Discovery for Ptychography via Evolutionary LLM Reasoning
Ptychography is a computational imaging technique widely used for high-resolution materials characterization, but high-quality reconstructions often require the use of regularization functions that largely remain manuall…
Code GenerationCONCUR: Benchmarking LLMs for Concurrent Code Generation
Leveraging Large Language Models (LLMs) for code generation has increasingly emerged as a common practice in the domain of software engineering. Relevant benchmarks have been established to evaluate the code generation c…
Code GenerationSWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration
Large language model (LLM)-powered agents have demonstrated strong capabilities in automating software engineering tasks such as static bug fixing. However, in the real world, the development of mature software is typica…
Code GenerationIn-Context Environments Induce Evaluation-Awareness in Language Models
Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}. This raises concerns…
Code GenerationCode Fingerprints: Disentangled Attribution of LLM-Generated Code
The rapid adoption of Large Language Models (LLMs) has transformed modern software development by enabling automated code generation at scale. While these systems improve productivity, they introduce new challenges for s…
Contrastive LearningCode Generation$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners
Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, by methods such as independently sampling and aggregating multiple solutions, results in significantly better task outcomes. How…
Code GenerationDOVA: Deliberation-First Multi-Agent Orchestration for Autonomous Research Automation
Large language model (LLM) agents have demonstrated remarkable capabilities in tool use, reasoning, and code generation, yet single-agent systems exhibit fundamental limitations when confronted with complex research task…
Code GenerationVibe Code Bench: Evaluating AI Models on End-to-End Web Application Development
Code generation has emerged as one of AI's highest-impact use cases, yet existing benchmarks measure isolated tasks rather than the complete "zero-to-one" process of building a working application from scratch. We introd…
Code GenerationHuman-Certified Module Repositories for the AI Age
Human-Certified Module Repositories (HCMRs) are introduced in this work as a new architectural model for constructing trustworthy software in the era of AI-assisted development. As large language models increasingly part…
Code GenerationStitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning
Modern machine learning (ML) workloads increasingly rely on GPUs, yet achieving high end-to-end performance remains challenging due to dependencies on both GPU kernel efficiency and host-side settings. Although LLM-based…
Reinforcement LearningCode GenerationGraph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization
Optimizing communication topology is fundamental to the efficiency and effectiveness of Large Language Model (LLM)-based Multi-Agent Systems (MAS). While recent approaches utilize reinforcement learning to dynamically co…
Reinforcement LearningCode GenerationLocally Coherent Parallel Decoding in Diffusion Language Models
Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models, offering sub-linear generation latency and bidirectional capabilities that are particularly appealing for code gener…
Code GenerationAI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework
Large Language Models (LLMs) demonstrate potentials for automating scientific code generation but face challenges in reliability, error propagation in multi-agent workflows, and evaluation in domains with ill-defined suc…
Prompt EngineeringCode GenerationAct-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation
Can a multimodal language model learn to manipulate physical objects by reasoning about its own failures-without gradient updates, demonstrations, or reward engineering? We argue the answer is yes, under conditions we ch…
Robot ManipulationCode GenerationMetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models
Discrete diffusion language models (dLLMs) generate text by iteratively denoising a masked sequence. However, standard dLLMs condition each denoising step solely on the current hard-masked sequence, while intermediate co…
Mathematical ReasoningCode GenerationInference-Time Safety For Code LLMs Via Retrieval-Augmented Revision
Large Language Models (LLMs) are increasingly deployed for code generation in high-stakes software development, yet their limited transparency in security reasoning and brittleness to evolving vulnerability patterns rais…
Code Generation