ModiGen: A Large Language Model-Based Workflow for Multi-Task Modelica Code Generation
cs.SE, cs.AI
Submitted: 2025-03-24
Updated: 2026-09-13
Code: https://github.com/modelica/ModelicaStandardLibrary
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen2.5-Coder Technical Report
- LLM4EFFI: Leveraging Large Language Models to Enhance Code Efficiency and Correctness
- A Problem-Oriented Perspective and Anchor Verification for Code Optimization
- Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization
- Evaluating Large Language Models Trained on Code
- Code Llama: Open Foundation Models for Code
- StarCoder 2 and The Stack v2: The Next Generation
- CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
- Gemini: A Family of Highly Capable Multimodal Models
- DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
- A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages
- LoRA: Low-Rank Adaptation of Large Language Models
- RLTF: Reinforcement Learning from Unit Test Feedback
- GRAG: Graph Retrieval-Augmented Generation
- GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties