UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development
Software development is a complex task that demands cooperation among agents with diverse roles. Large language models (LLMs) have enabled autonomous multi-agent software development frameworks that leverage role-based collaboration to automate requirements analysis, coding, testing, and refinement. However, existing approaches typically assume that intermediate agent outputs are equally reliable, leaving them vulnerable to hallucination propagation, where incorrect decisions generated in early development phases are transferred to downstream agents and negatively impact final software quality
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorTemitayo Olamilekan Ogunsusi →
UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development
- Linked via arxiv authorLijun Qian →
UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development
- Linked via arxiv authorXishuang Dong →
UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development