# Completing A Systematic Review in Hours instead of Months with Interactive AI Agents

arXiv: https://arxiv.org/abs/2504.14822 · HTML: https://mlsanity.com/paper/2504.14822/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 51 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 9 of 9)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LitLLM: A Toolkit for Scientific Literature Review](https://mlsanity.com/paper/2402.01788/) (2024)
- [ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary](https://mlsanity.com/paper/2403.02574/) (2024)
- [Instruct Large Language Models to Generate Scientific Literature Survey Step by Step](https://mlsanity.com/paper/2408.07884/) (2024)
- [pathfinder: A Semantic Framework for Literature Review and Knowledge Discovery in Astronomy](https://mlsanity.com/paper/2408.01556/) (2024)
- [From Information to Choice: A Critical Inquiry Into Visualization Tools for Decision Making](https://mlsanity.com/paper/2307.08326/) (2023)
- [Toward a deeper understanding of Visualization through keyword analysis](https://mlsanity.com/paper/1408.3297/) (2014)
- [VADIS: A Visual Analytics Pipeline for Dynamic Document Representation and Information-Seeking](https://mlsanity.com/paper/2504.05697/) (2025)
- [HINTs: Sensemaking on large collections of documents with Hypergraph visualization and INTelligent agents](https://mlsanity.com/paper/2403.02752/) (2024)

## Built on by (most cited first, 5 of 5)

- [AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis](https://mlsanity.com/paper/2606.02403/) (2026)
- [Meow: End-to-End Outline Writing for Automatic Academic Survey](https://mlsanity.com/paper/2509.19370/) (2025)
- [Probing the Future of Meta-Analysis: Eliciting Design Principles via an Agentic Research IDE](https://mlsanity.com/paper/2601.18239/) (2026)
- [SurveyAgent-HKA: A multi-agent framework for scientific survey generation with LLMs and human knowledge augmentation](https://mlsanity.com/paper/2609.05938/) (2026)
- [LabCompiler: A Framework for Verifiable Human-Machine Laboratory Execution from Imperfect Protocols](https://mlsanity.com/paper/2610.19550/) (2026)

## Abstract (arXiv)

Systematic reviews (SRs) are vital for evidence-based practice in high stakes disciplines, such as healthcare, but are often impeded by intensive labors and lengthy processes that can take months to complete. Due to the high demand for domain expertise, existing automatic summarization methods fail to accurately identify relevant studies and generate high-quality summaries. To that end, we introduce InsightAgent, a human-centered interactive AI agent powered by large language models that revolutionize this workflow. InsightAgent partitions a large literature corpus based on semantics and employs a multi-agent design for more focused processing of literature, leading to significant improvement in the quality of generated SRs. InsightAgent also provides intuitive visualizations of the corpus and agent trajectories, allowing users to effortlessly monitor the actions of the agent and provide real-time feedback based on their expertise. Our user studies with 9 medical professionals demonstrate that the visualization and interaction mechanisms can effectively improve the quality of synthesized SRs by 27.2%, reaching 79.7% of human-written quality. At the same time, user satisfaction is improved by 34.4%. With InsightAgent, it only takes a clinician about 1.5 hours, rather than months, to complete a high-quality systematic review.