Saved in:
Bibliographic Details
Main Author: Zhang, Peng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.14629
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911518459691008
author Zhang, Peng
author_facet Zhang, Peng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14629
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ResearchPilot: A Local-First Multi-Agent System for Literature Synthesis and Related Work Drafting
Zhang, Peng
Information Retrieval
Artificial Intelligence
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.
title ResearchPilot: A Local-First Multi-Agent System for Literature Synthesis and Related Work Drafting
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2603.14629