BehaviorSFT: Behavioral Token Conditioning for Health Agents Across the Proactivity Spectrum

Yubin Kim, Zhiyuan Hu, Hyewon Jeong, Eugene W Park, Shuyue Stella Li, Chanwoo Park, Shiyun Xiong, MingYu Lu, Hyeonhoon Lee, Xin Liu, Daniel McDuff, Cynthia Breazeal, Samir Tulebaev, Hae Won Park


Abstract
Large Language Models (LLMs) as agents require careful behavioral adaptation. While adept at reactive tasks (e.g., medical reasoning), LLMs often struggle with proactive engagement, like unprompted identification of critical missing information or risks. We introduce **BehaviorBench**, a comprehensive dataset to evaluate agent behaviors across a clinical assistance spectrum. To rigorously test the current models, we also introduce **BehaviorBench-Hard**, a challenging subset where the performance of state-of-the-art models drops significantly, revealing weaknesses. To address these challenges, we propose **BehaviorSFT**, a novel training strategy using behavioral tokens to explicitly condition LLMs for dynamic behavioral selection which boosts performance on both benchmarks. Crucially, a blind clinician evaluation confirmed that our trained agents exhibit more realistic clinical behavior, striking a superior balance between helpful proactivity and necessary restraint versus standard fine-tuning or explicitly instructed agents. Project Page: https://behavior-adaptation.github.io/
Anthology ID:
2025.findings-emnlp.520
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9789–9817
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.520/
DOI:
Bibkey:
Cite (ACL):
Yubin Kim, Zhiyuan Hu, Hyewon Jeong, Eugene W Park, Shuyue Stella Li, Chanwoo Park, Shiyun Xiong, MingYu Lu, Hyeonhoon Lee, Xin Liu, Daniel McDuff, Cynthia Breazeal, Samir Tulebaev, and Hae Won Park. 2025. BehaviorSFT: Behavioral Token Conditioning for Health Agents Across the Proactivity Spectrum. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 9789–9817, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
BehaviorSFT: Behavioral Token Conditioning for Health Agents Across the Proactivity Spectrum (Kim et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.520.pdf
Checklist:
 2025.findings-emnlp.520.checklist.pdf