3 papers
cs.CV2026
Towards Fully Automated Medical Imaging Code Generation via Validation-based Context Engineering
Zixiao Zhao, Jing Sun, Zhe Hou +5
Large language models (LLMs) have demonstrated considerable promise in program generation for small-scale and conventional application development; however, they remain limited whe…
cs.CR2025
Adaptive Plan-Execute Framework for Smart Contract Security Auditing
Zhiyuan Wei, Jing Sun, Zijian Zhang +2
Large Language Models (LLMs) have shown great promise in code analysis and auditing; however, they still struggle with hallucinations and limited context-aware reasoning. We introd…
cs.SE2024
MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming
Zixiao Zhao, Jing Sun, Zhe Hou +4
With the rapid advancement of Large Language Models (LLMs), LLM-based approaches have demonstrated strong problem-solving capabilities across various domains. However, in automatic…