TheraAgent: Self-Improving Therapeutic Agent for Precise and Comprehensive Treatment Planning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910197779267584 |
|---|---|
| author | Li, Junkai Lai, Yunghwei Zhu, Tianyi Lee, Zheng Long Ma, Weizhi Liu, Yang |
| author_facet | Li, Junkai Lai, Yunghwei Zhu, Tianyi Lee, Zheng Long Ma, Weizhi Liu, Yang |
| contents | Formulating a treatment plan is inherently a complex reasoning and refinement task rather than a simple generation problem. However, existing large language models (LLMs) mainly rely on one-shot output without explicit verification, which may result in rough, incomplete, and potentially unsafe treatment plans. To address these limitations, we propose TheraAgent, an agentic framework that replaces one-shot generation with an iterative generate-judge-refine pipeline. By mirroring the actual reasoning process of human experts who iteratively revise treatment plans, our framework progressively transforms coarse and incomplete drafts into precise, comprehensive, and safer therapeutic regimens. To facilitate the critical judge component, we introduce TheraJudge, a treatment-specific evaluation module integrated into the inference loop to enforce clinical standards. Experiments show TheraAgent achieves state-of-the-art results on HealthBench, leading in Accuracy and Completeness. In expert evaluations, it attains an 86% win rate against physicians, with superior Targeting and Harm Control. Moreover, the highly agreement between TheraJudge and HealthBench evaluations confirms the reliability of our framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_05963 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TheraAgent: Self-Improving Therapeutic Agent for Precise and Comprehensive Treatment Planning Li, Junkai Lai, Yunghwei Zhu, Tianyi Lee, Zheng Long Ma, Weizhi Liu, Yang Artificial Intelligence Computation and Language Formulating a treatment plan is inherently a complex reasoning and refinement task rather than a simple generation problem. However, existing large language models (LLMs) mainly rely on one-shot output without explicit verification, which may result in rough, incomplete, and potentially unsafe treatment plans. To address these limitations, we propose TheraAgent, an agentic framework that replaces one-shot generation with an iterative generate-judge-refine pipeline. By mirroring the actual reasoning process of human experts who iteratively revise treatment plans, our framework progressively transforms coarse and incomplete drafts into precise, comprehensive, and safer therapeutic regimens. To facilitate the critical judge component, we introduce TheraJudge, a treatment-specific evaluation module integrated into the inference loop to enforce clinical standards. Experiments show TheraAgent achieves state-of-the-art results on HealthBench, leading in Accuracy and Completeness. In expert evaluations, it attains an 86% win rate against physicians, with superior Targeting and Harm Control. Moreover, the highly agreement between TheraJudge and HealthBench evaluations confirms the reliability of our framework. |
| title | TheraAgent: Self-Improving Therapeutic Agent for Precise and Comprehensive Treatment Planning |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2605.05963 |