ChatPPG.
Join free
First page or project page of “HealthJev: A Self-Evolving Agent for Longitudinal Personal Health Management (Guo et al., Research Square rs-11605391)” (opens in a new tab)

Paperdoi:10.21203/rs.3.rs-11605391/v1

HealthJev: A Self-Evolving Agent for Longitudinal Personal Health Management (Guo et al., Research Square rs-11605391)

Preprint2026Added Nov 6, 2026

  • HG
  • HL
  • JD
  • TJ
  • JH
  • YW
  • ZW
  • JS
  • +4

Authors: Hongcheng Guo, Haoran Li, Jiebi Deng, Tong Jin, Jinghong Han, Yuxin Wang, Zexin Wang, Jinyu Sun, Qingyi Si, Weikang Gong,

+2 moreXiahai Zhuang, Jia You

Research Square preprint rs-11605391 v1

Publisher (opens in a new tab) Cite
Open codeOpen weights
First page or project page of “HealthJev: A Self-Evolving Agent for Longitudinal Personal Health Management (Guo et al., Research Square rs-11605391)” (opens in a new tab)

Hongcheng Guo et al., "A Self-Evolving Agent for Longitudinal Personal Health Management", doi:10.21203/rs.3.rs-11605391/v1, CC BY 4.0

TL;DR

Open-source self-evolving personal health agent: shared safety rules / medical knowledge separated from a private longitudinal memory; distills lessons across encounters. JevGate-9B (Qwen3.5-9B-Base + LoRA r=16 + 256-d pointer head) is the System-One admission gate for long-term memory. Ships a longitudinal MIMIC-IV benchmark and a six-task biomedical suite (per README 2026-10-26).

  • Form factor: agent / software

Abstract

Medical large language models and agents show strong single-encounter question answering and evidence interpretation but struggle to accumulate and govern experience across encounters. We present HealthJev, an open-source agent separating shared safety rules and medical knowledge from a private longitudinal memory and distilling lessons from completed cases. To filter out erroneous lessons before they affect future behaviour, we self-train JevGate, a lightweight System-One model that decides which lessons enter memory; each decision takes a median of 86 milliseconds and about 1,000 input tokens, sustaining experience accumulation at negligible run-time overhead. On a longitudinal benchmark of 90-day simulated daily interactions for 20 users built from real MIMIC-IV trajectories, HealthJev outperformed a memory-free ReAct agent and three memory-augmented frameworks, with all paired comparisons significant. Across six tasks spanning clinical records, medical imaging, genomics and clinical text, HealthJev improved every task with a mean gain of 13.3 percentage points over the base condition, surpassing all baselines. The frozen library transferred to six further backbones with macro-average gains of 6.8 to 15.1 percentage points, and one task's library brought gains on other tasks. These results indicate that governed, self-evolving memory supports longitudinal personal health management beyond single encounters. HealthJev is publicly available at https://github.com/HC-Guo/Self-Evolving_HealthJev.

Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: https://creativecommons.org/licenses/by/4.0/

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Signals

EHRTextimagingomicswearable summaries

Keywords

LLM AgentHealth AgentSelf EvolvingWearable AdjacentMITJevGateMIMIC IV

How it works

How Method works: Setup → Method → TargetSetup: Signals (text, EHR, wearable summaries, imaging, omics); Form factor (agent / software). Method: Method (Language-aligned).SetupSignals: text, EHR, wearable summaries, imaging, omicsSignalstext, EHR, wearable summaries…Form factor: agent / softwareForm factoragent / softwareMethodMethodLanguage-aligned

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Guo, H., Li, H., Deng, J., Jin, T., Han, J., Wang, Y., Wang, Z., Sun, J., Si, Q., Gong, W., Zhuang, X., & You, J. (2026). HealthJev: A Self-Evolving Agent for Longitudinal Personal Health Management (Guo et al., Research Square rs-11605391). Research Square preprint rs-11605391 v1. https://doi.org/10.21203/rs.3.rs-11605391/v1
Guo, Hongcheng, Haoran Li, Jiebi Deng, Tong Jin, Jinghong Han, Yuxin Wang, and Zexin Wang, et al. 2026. "HealthJev: A Self-Evolving Agent for Longitudinal Personal Health Management (Guo et al., Research Square rs-11605391)." Research Square preprint rs-11605391 v1. https://doi.org/10.21203/rs.3.rs-11605391/v1.
Guo, H., Li, H., Deng, J., Jin, T., Han, J., Wang, Y. and Wang, Z. et al. (2026) 'HealthJev: A Self-Evolving Agent for Longitudinal Personal Health Management (Guo et al., Research Square rs-11605391)', Research Square preprint rs-11605391 v1. doi: 10.21203/rs.3.rs-11605391/v1.
Guo, Hongcheng, et al. "HealthJev: A Self-Evolving Agent for Longitudinal Personal Health Management (Guo et al., Research Square rs-11605391)." Research Square preprint rs-11605391 v1, 2026. https://doi.org/10.21203/rs.3.rs-11605391/v1.
H. Guo et al., "HealthJev: A Self-Evolving Agent for Longitudinal Personal Health Management (Guo et al., Research Square rs-11605391)," Research Square preprint rs-11605391 v1, 2026, doi: 10.21203/rs.3.rs-11605391/v1.
@misc{guo2026healthjev,
  title         = {{HealthJev: A Self-Evolving Agent for Longitudinal Personal Health Management (Guo et al., Research Square rs-11605391)}},
  author        = {Guo, Hongcheng and Li, Haoran and Deng, Jiebi and Jin, Tong and Han, Jinghong and Wang, Yuxin and Wang, Zexin and Sun, Jinyu and Si, Qingyi and Gong, Weikang and Zhuang, Xiahai and You, Jia},
  year          = {2026},
  howpublished  = {Research Square preprint rs-11605391 v1},
  doi           = {10.21203/rs.3.rs-11605391/v1}
}

Added to the ChatPPG research hub

Same tasks, data and authors