Beyond Correlation: Towards Causal Large Language Model Agents in Biomedicine
This research agenda addresses the need for reliable AI partners in biomedicine by bridging causal concepts and foundation models, though it is incremental as it outlines challenges and opportunities without presenting new results.
The paper tackles the problem of large language models lacking causal understanding in biomedicine by proposing causal LLM agents that integrate multimodal data and intervention-based reasoning, aiming to unlock transformative opportunities like accelerating drug discovery and enabling personalized medicine.
Large Language Models (LLMs) show promise in biomedicine but lack true causal understanding, relying instead on correlations. This paper envisions causal LLM agents that integrate multimodal data (text, images, genomics, etc.) and perform intervention-based reasoning to infer cause-and-effect. Addressing this requires overcoming key challenges: designing safe, controllable agentic frameworks; developing rigorous benchmarks for causal evaluation; integrating heterogeneous data sources; and synergistically combining LLMs with structured knowledge (KGs) and formal causal inference tools. Such agents could unlock transformative opportunities, including accelerating drug discovery through automated hypothesis generation and simulation, enabling personalized medicine through patient-specific causal models. This research agenda aims to foster interdisciplinary efforts, bridging causal concepts and foundation models to develop reliable AI partners for biomedical progress.