Metraipolis › archive › dc_2a4efc330f98
Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction — arXiv:2610.21449
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21449
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:03:21.475Z
- SHA-256 of the archived text
515c6d714c8ce22993bf699846da199dd919336e826d5ce9c5ba883a799868a5- Stable URL of this page
https://metraipolis.com/documento/dc_2a4efc330f98
How to cite
Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction — arXiv:2610.21449 — arXiv (en), https://arxiv.org/abs/2610.21449 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a4efc330f98 (Metraipolis archive dc_2a4efc330f98, sha256 515c6d714c8ce22993bf699846da199dd919336e826d5ce9c5ba883a799868a5)
BibTeX
@misc{dc2a4efc330f98,
title = {Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction — arXiv:2610.21449},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21449},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a4efc330f98; sha256 515c6d714c8ce22993bf699846da199dd919336e826d5ce9c5ba883a799868a5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21449. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) can reason over both structured measurements and free-text records, which makes them attractive for emergency department (ED) prediction. However, most existing LLMs still fall short of conventional ML methods like trees on EHR-based prediction tasks. Our controlled analysis traces this gap to two weaknesses: LLMs do not select informative features, and they misjudge what numerical values imply for risk even when given the right features. We propose TIR-EC, a tool-integrated reinforcement learning framework that addresses both. TIR-EC exposes EHR feature groups as tools the LLM can call. It trains the LLM with rewards from a gradient-boosted tree teacher, which provides a reference set of informative tools and a graded risk target. TIR-EC also distills task-specific clinical skills into the model weights through a reverse curriculum that gradually removes the skills from the prompt during RL process. Evaluation on three clinical prediction tasks shows that our 4B agent achieves the highest macro F1 of all compared models, outperforms conventional ML baselines, and is competitive with much larger frontier LLMs. Further analysis shows that TIR-EC selects more useful evidence with fewer tool calls and combines measurements more effectively. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.21449 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:44:17.745Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).