# ResearchPilot: A Local-First Multi-Agent System for Literature Synthesis and Related Work Drafting

arXiv: https://arxiv.org/abs/2603.14629 · HTML: https://mlsanity.com/paper/2603.14629/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 6 references that are in the map.
- First posted on arXiv 15 Mar 2026.

## Builds on (most cited first, 4 of 4)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [The Semantic Scholar Open Data Platform](https://mlsanity.com/paper/2301.10140/) (2023)

## Built on by (most cited first, 2 of 2)

- [RepoReviewer: A Local-First Multi-Agent Architecture for Repository-Level Code Review](https://mlsanity.com/paper/2603.16107/) (2026)
- [Automated Analysis Framework for Multilingual Climate-Health Literature Based on Multi-Agent Large Language Model](https://mlsanity.com/paper/2608.27998/) (2026)

## Abstract (arXiv)

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.