Live intelligence

Latest AI updates

1 updates
Research

PARIS: A multi-agent LLM framework for end-to-end, PRISMA-guided systematic literature reviews with pre-synthesis corpus quality assessment

PARIS is an open-source framework in which a conductor agent running in Claude Code orchestrates 15 specialized LLM agents across a systematic review workflow, from research scoping to manuscript draft export. Agents coordinate through persisted artifacts validated by the conductor, while retrieval, bibliometric analysis and scoring are delegated to deterministic Python utilities; three human checkpoints gate inclusion, corpus adequacy and synthesis outline. The paper introduces QualityScore, a 0-100 pre-synthesis index combining network, bibliometric, semantic and process sub-scores, and reports two case studies plus audit findings on failure modes. The authors state that output quality has so far been judged only by an internal reviewer agent and that independent validation against human reviews is the next step.

multi-agent systemsLLM agentssystematic literature review