PARIS: A multi-agent LLM framework for end-to-end, PRISMA-guided systematic literature reviews with pre-synthesis corpus quality assessment
- Published
- Source
- arXiv
- Paper number
- 1440
- Field
- AI Agents
- arXiv ID
- 2611.12222
Key points
- The authors built PARIS, a framework where a conductor agent running in Claude Code orchestrates 15 specialized large language model (LLM) agents.
- All agents communicate exclusively through persisted artifacts, and the conductor validates each file before the next step.
- Three human checkpoints keep study inclusion, corpus adequacy and the synthesis outline under human authority.
- QualityScore grades the corpus from 0 to 100 before synthesis, and corpus improvements raised it from 74.6 to 81.9 in the first case study.
- The second case study included 123 of 131 records and recorded a QualityScore of 69.1.
- The authors' audits exposed failure modes such as incomplete retrieval, counts drifting between agents and unrecorded checkpoint decisions, and PARIS fully supports 8 of the 27 PRISMA 2020 items.
Paper links
External research summaries. These are not HDATF publications or measured product results.