AI RESEARCH
Code Researcher: Deep Research Agent for Large Systems Code and Commit History
arXiv CS.AI
•
ArXi:2506.11060v2 Announce Type: replace-cross Large Language Model (LLM)-based coding agents have shown promising results on coding benchmarks, but their effectiveness on systems code remains underexplored. Due to the size and complexities of systems code, making changes to a systems codebase requires researching about many pieces of context, derived from the large codebase and its massive commit history, before making changes.