ResearchPilot: A Local-First Multi-Agent System for Literature Synthesis and Related Work Drafting
This is an incremental systems contribution for researchers needing assistance in literature synthesis and drafting.
The authors tackled the problem of automating literature reviews by developing ResearchPilot, a local-first multi-agent system that retrieves papers, extracts findings, synthesizes patterns, and drafts related-work sections based on a research question, with evaluation conducted through automated tests and end-to-end runs.
ResearchPilot is an open-source, self-hostable multi-agent system for literature-review assistance. Given a natural-language research question, it retrieves papers from Semantic Scholar and arXiv, extracts structured findings from paper abstracts, synthesizes cross-paper patterns, and drafts a citation-aware related-work section. The system combines FastAPI, Next.js, DSPy, SQLite, and Qdrant in a local-first architecture that supports bring-your-own-key model access and remote-or-local embeddings. This paper describes the system design, typed agent interfaces, persistence and history-search mechanisms, and the engineering tradeoffs involved in building a transparent research assistant. Rather than claiming algorithmic novelty, we present ResearchPilot as a systems contribution and evaluate it through automated tests and end-to-end local runs. We discuss limitations including external API rate limits, abstract-only extraction, incomplete corpus coverage, and the lack of citation verification.