An Agentic LLM Framework for Autonomous Surgical Continuum Monitoring: ReAct-Driven Tool-Use Agents for Presurgical, Intraoperative, and Postsurgical Cardiopulmonary Care
Charalampia Pylarinou, Lefteris Gortzis, Vasileios Leivaditis, Elias Liolis, Andreas Antzoulas, Spyros Papadoulas, Konstantinos Nikolakopoulos, Ioannis Panagiotopoulos, Sofoklis Mitsos, Periklis Tomos, Efstratios Koletsis, Francesk Mulita · 2026
Read An Agentic LLM Framework for Autonomous Surgical Continuum Monitoring: ReAct-Driven Tool-Use Agents for Presurgical, Intraoperative, and Postsurgical Cardiopulmonary Care by Charalampia Pylarinou, Lefteris Gortzis, Vasileios Leivaditis, Elias Liolis, Andreas Antzoulas, Spyros Papadoulas, Konstantinos Nikolakopoulos, Ioannis Panagiotopoulos, Sofoklis Mitsos, Periklis Tomos, Efstratios Koletsis, Francesk Mulita (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13295611.txt.
Description
Charalampia Pylarinou and a large team design reasoning software agents for surgical care in a 2026 article. Older multi-agent systems follow fixed rule trees and stumble on new situations across the long surgical journey. Their framework swaps fixed rules for language model agents that reason, fetch evidence, and check their own thinking.
Six agents cover care before, during, and after heart-lung surgery, each with a defined tool set and authority limits. Every decision that changes the care path must pass a confidence gate with human approval. A supervisor agent settles competing resource requests, aiming to cut false alerts while keeping patients safe in unclear cases.
Catalog record
| CREATOR | Charalampia Pylarinou, Lefteris Gortzis, Vasileios Leivaditis, Elias Liolis, Andreas Antzoulas, Spyros Papadoulas, Konstantinos Nikolakopoulos, Ioannis Panagiotopoulos, Sofoklis Mitsos, Periklis Tomos, Efstratios Koletsis, Francesk Mulita |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 72804 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |