Abstract
Longitudinal clinical reasoning requires large language models (LLMs) to identify and integrate relevant evidence distributed across extended patient histories. Although long-context models can process increasingly large amounts of information, providing more history does not necessarily make relevant evidence more accessible or improve reasoning. We compare five context strategies (Full, Recent, Episodic, Semantic, and Hybrid) on MedLoCoMo across four open-weight LLMs, examining answer correctness, robustness to query-evidence distance, and abstention on questions with unsupported premises. Episodic and Hybrid generally achieve the strongest overall accuracy, while Recent Context degrades most as supporting evidence becomes more distant; Episodic and Hybrid maintain the highest accuracy at long distances. Analysis of adversarial questions further shows that strong performance on answerable questions does not necessarily translate to successful abstention when the available history does not support the requested conclusion. These findings show that reliable longitudinal reasoning depends not only on how much history an LLM can access, but critically on how relevant evidence is selected and presented for reasoning.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Akinrele, T., Golilarz, N. A., Neupane, S., Mittal, S., & Rahimi, S. (2026). Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning. https://omanscience.com/en/articles/can-llms-reason-over-long-horizons-an-empirical-evaluation-of-context-strategies-for-longitudinal-clinical-reasoning
MLA 9
Akinrele, Taye, et al. "Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning." https://omanscience.com/en/articles/can-llms-reason-over-long-horizons-an-empirical-evaluation-of-context-strategies-for-longitudinal-clinical-reasoning.
Chicago (author–date)
Akinrele, Taye, Noorbakhsh Amiri Golilarz, Subash Neupane, Sudip Mittal, and Shahram Rahimi. 2026. "Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning." https://omanscience.com/en/articles/can-llms-reason-over-long-horizons-an-empirical-evaluation-of-context-strategies-for-longitudinal-clinical-reasoning.
Harvard
Akinrele, T., Golilarz, N. A., Neupane, S., Mittal, S. and Rahimi, S. (2026) 'Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning', Available at: https://omanscience.com/en/articles/can-llms-reason-over-long-horizons-an-empirical-evaluation-of-context-strategies-for-longitudinal-clinical-reasoning.
Vancouver
Akinrele T, Golilarz NA, Neupane S, Mittal S, Rahimi S. Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning. https://omanscience.com/en/articles/can-llms-reason-over-long-horizons-an-empirical-evaluation-of-context-strategies-for-longitudinal-clinical-reasoning
IEEE
T. Akinrele, N. A. Golilarz, S. Neupane, S. Mittal, and S. Rahimi, "Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning," https://omanscience.com/en/articles/can-llms-reason-over-long-horizons-an-empirical-evaluation-of-context-strategies-for-longitudinal-clinical-reasoning.