mlsanityData to 7 Oct 2026

Causal-Enhanced AI Agents for Medical Research Screening

arXiv 2601.02814 ↗First posted 6 Jan 2026cs.AIcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 24 references that are in the map. First posted on arXiv 6 Jan 2026.

Builds on

9 of 24 references.

References · 9

  1. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 456
  2. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  3. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
  4. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 144
  5. 2024Efficient Causal Graph Discovery Using Large Language Modelscited by 51
  6. 2025Mitigating Hallucinations in Large Language Models via Causal Reasoningcited by 13
  7. 2024CausalGraph2LLM: Evaluating LLMs for Causal Queriescited by 12
  8. 2025CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generationcited by 12
  9. 2025CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generationcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DoAtlas-1: A Causal Compilation Paradigm for Clinical AI
  2. 2025Accelerating Causal Network Discovery of Alzheimer Disease Biomarkers via Scientific Literature-based Retrieval Augmented Generation
  3. 2026Making medical vision-language models think causally across modalities with retrieval-augmented cross-modal reasoning
  4. 2025An AI-Driven Live Systematic Reviews in the Brain-Heart Interconnectome: Minimizing Research Waste and Advancing Evidence Synthesis
  5. 2026EviDAG: Auditable Causal DAG Authoring with Biomedical Literature
  6. 2025Causal Reinforcement Learning based Agent-Patient Interaction with Clinical Domain Knowledge
  7. 2025DEMENTIA-PLAN: An Agent-Based Framework for Multi-Knowledge Graph Retrieval-Augmented Generation in Dementia Care
  8. 2026When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models