# Causal-Enhanced AI Agents for Medical Research Screening

arXiv: https://arxiv.org/abs/2601.02814 · HTML: https://mlsanity.com/paper/2601.02814/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 6 Jan 2026.

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

- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation](https://mlsanity.com/paper/2404.00610/) (2024)
- [Efficient Causal Graph Discovery Using Large Language Models](https://mlsanity.com/paper/2402.01207/) (2024)
- [Mitigating Hallucinations in Large Language Models via Causal Reasoning](https://mlsanity.com/paper/2508.12495/) (2025)
- [CausalGraph2LLM: Evaluating LLMs for Causal Queries](https://mlsanity.com/paper/2410.15939/) (2024)
- [CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.19878/) (2025)
- [CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.12560/) (2025)

## Abstract (arXiv)

Systematic reviews are essential for evidence-based medicine, but reviewing 1.5 million+ annual publications manually is infeasible. Current AI approaches suffer from hallucinations in systematic review tasks, with studies reporting rates ranging from 28--40% for earlier models to 2--15% for modern implementations which is unacceptable when errors impact patient care. We present a causal graph-enhanced retrieval-augmented generation system integrating explicit causal reasoning with dual-level knowledge graphs. Our approach enforces evidence-first protocols where every causal claim traces to retrieved literature and automatically generates directed acyclic graphs visualizing intervention-outcome pathways. Evaluation on 234 dementia exercise abstracts shows CausalAgent achieves 95% accuracy, 100% retrieval success, and zero hallucinations versus 34% accuracy and 10% hallucinations for baseline AI. Automatic causal graphs enable explicit mechanism modeling, visual synthesis, and enhanced interpretability. While this proof-of-concept evaluation used ten questions focused on dementia exercise research, the architectural approach demonstrates transferable principles for trustworthy medical AI and causal reasoning's potential for high-stakes healthcare.