---
title: "THGAgents: Traceable Biomedical Hypothesis Generation via Dynamic Causal Reasoning"
authors:
  - "Mingjian Yang"
  - "Kun Dong"
  - "Kevin Lim"
  - "Juan Liu"
doi: "10.24963/ijcai.2026/776"
url: "https://ijcai.org/proceedings/2026/776"
pdf: "https://ijcai.org/proceedings/2026/0776.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6975-6983"
track: "AI and Health"
keywords:
  - "Medical knowledge representation: Medical knowledge representation"
  - "LLM in medicine: LLM in medicine"
---

# THGAgents: Traceable Biomedical Hypothesis Generation via Dynamic Causal Reasoning

Mingjian Yang, Kun Dong, Kevin Lim, Juan Liu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6975-6983. DOI: [10.24963/ijcai.2026/776](https://doi.org/10.24963/ijcai.2026/776)

## Abstract

While Large Language Models (LLMs) offer promise in scientific discovery, leveraging LLMs to drive biomedical research requires the scientific discovery process to be performed in combination with cutting-edge biomedical research and rigorous mechanistic causal chains. As such, both current Retrieval-augmented generation methods lacking causal reasoning capabilities, and the static traditional knowledge graphs failing to reflect evolving scientific knowledge, present obstacles to utilizing LLMs as scientific discovery tools. In response to these ongoing challenges, we present THGAgents. THGAgents utilize collaborative and dynamically updating agents to build a Traceable Causal Knowledge Graph, which serves as the foundation for the evidence-based knowledge structure. Crucially, we employ an LLM-driven heuristic search algorithm to traverse the complex network, balancing both novelty and rigor to deduce strict, evidence-based mechanistic causal chains.  Additionally, THGAgents utilize a generator-critic loop to support hypothesis refinement.  In experimental benchmarks across both cancer systems and neuroscience, THGAgents achieved up to a 0.80 hit rate in predicting validated scientific discoveries, providing an almost 9.5% increase in hypothesis quality scores versus current state-of-the-art systems, and decreasing the mechanistic hallucination rate to 1.12%. Our code is available at https://github.com/yangCode-res/THGAgents/.