Search papers, labs, and topics across Lattice.
5
0
6
8
Agent Plans in open-source repositories reveal critical insights into how AI coding tools can be effectively guided through structured task-oriented artifacts.
Most AI agent skills are reused verbatim, with over half never modified, revealing a critical gap in how we think about skill evolution and maintenance.
Stale context in AI configuration files affects 23% of software repositories, revealing a critical vulnerability in AI-assisted development workflows.
Enumerating all potential issues in code reviews can boost refinement accuracy by over 10 percentage points compared to traditional methods.
LLM-based code summarization delivers richer semantic understanding, but rule-based methods still win on conciseness and reproducibility.
