Abstract
Early-stage computational drug discovery requires coordinating heterogeneous scientific tools across multi-step workflows. We present a lightweight, tool-augmented framework in which a locally deployable compact language model plans calls to 18 modular tools. A Unified Molecular Schema maintains shared molecular records, while a plug-in interface supports tool replacement and extension. We construct 1,263 manually refined query-plan pairs through workflow-graph path coverage and apply LoRA fine-tuning to three compact model families. Under the query-level split, all fine-tuned models generate fully parseable and schema-compliant plans on 47 held-out cross-group queries. Llama 3.2-3B achieves a tool-selection F1 of 0.998, sequence exact match of 0.979, and argument F1 of 0.960. Under the stricter workflow-grouped split, which excludes identical ordered tool sequences across partitions, sequence exact match reaches 0.452 to 0.548, highlighting the remaining difficulty for compact models in generating complete workflow paths unseen during training. These results demonstrate the feasibility of compact, locally deployable planning while identifying compositional generalization as an important direction for further improvement.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Liang, T., Chang, J., Frangi, A. F., Hoque, M. I., & Bryce, R. A. (2026). Toward a Locally Deployable Agentic Co-Scientist: Small-Model Planning for Early-Stage Drug Discovery. https://omanscience.com/en/articles/toward-a-locally-deployable-agentic-co-scientist-small-model-planning-for-early-stage-drug-discovery
MLA 9
Liang, Tian, et al. "Toward a Locally Deployable Agentic Co-Scientist: Small-Model Planning for Early-Stage Drug Discovery." https://omanscience.com/en/articles/toward-a-locally-deployable-agentic-co-scientist-small-model-planning-for-early-stage-drug-discovery.
Chicago (author–date)
Liang, Tian, Jiayu Chang, Alejandro F. Frangi, Mobarak I. Hoque, and Richard A. Bryce. 2026. "Toward a Locally Deployable Agentic Co-Scientist: Small-Model Planning for Early-Stage Drug Discovery." https://omanscience.com/en/articles/toward-a-locally-deployable-agentic-co-scientist-small-model-planning-for-early-stage-drug-discovery.
Harvard
Liang, T., Chang, J., Frangi, A. F., Hoque, M. I. and Bryce, R. A. (2026) 'Toward a Locally Deployable Agentic Co-Scientist: Small-Model Planning for Early-Stage Drug Discovery', Available at: https://omanscience.com/en/articles/toward-a-locally-deployable-agentic-co-scientist-small-model-planning-for-early-stage-drug-discovery.
Vancouver
Liang T, Chang J, Frangi AF, Hoque MI, Bryce RA. Toward a Locally Deployable Agentic Co-Scientist: Small-Model Planning for Early-Stage Drug Discovery. https://omanscience.com/en/articles/toward-a-locally-deployable-agentic-co-scientist-small-model-planning-for-early-stage-drug-discovery
IEEE
T. Liang, J. Chang, A. F. Frangi, M. I. Hoque, and R. A. Bryce, "Toward a Locally Deployable Agentic Co-Scientist: Small-Model Planning for Early-Stage Drug Discovery," https://omanscience.com/en/articles/toward-a-locally-deployable-agentic-co-scientist-small-model-planning-for-early-stage-drug-discovery.