Metraipolis › archive › dc_c8b2be6c2a76

ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech Assessment — arXiv:2608.06110

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06110
License (as archived)
CC0-1.0
Archived
2026-10-25T21:31:21.311Z
SHA-256 of the archived text
190511a59d9ef653f2444546162c3c779413e4b069a5c3689ad445ae2821fa71
Stable URL of this page
https://metraipolis.com/documento/dc_c8b2be6c2a76

How to cite

ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech Assessment — arXiv:2608.06110 — arXiv (en), https://arxiv.org/abs/2608.06110 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8b2be6c2a76 (Metraipolis archive dc_c8b2be6c2a76, sha256 190511a59d9ef653f2444546162c3c779413e4b069a5c3689ad445ae2821fa71)
BibTeX
@misc{dcc8b2be6c2a76,
  title = {ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech Assessment — arXiv:2608.06110},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06110},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8b2be6c2a76; sha256 190511a59d9ef653f2444546162c3c779413e4b069a5c3689ad445ae2821fa71},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06110. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper presents ECHO (Enhanced Care & Health Observer), a locally-deployable conversational health assistant for long-term chronic care management. ECHO integrates three complementary software modules developed under shared supervision as a unified system. The core module is an agentic chatbot built on a ReAct loop orchestrated via LangGraph, equipped with 17 clinical tools and a temporal knowledge graph for persistent cross-session memory; it achieves a 94.9% tool-execution pass rate across a 59-scenario benchmark with GPT-5 Mini. A two-stage hybrid safety layer intercepts all incoming queries: a rule-based layer handles explicit crisis signals and jailbreak attempts in under 1ms, while a signed graph neural network (GNN) with APPNP-style propagation classifies boundary cases by clinical intent, achieving 88.8% accuracy and 90.6% unsafe recall on a 2,537-query annotated Turkish health dataset while outperforming zero-shot LLM baselines including Llama 3.3 70B. A multimodal speech assessment module combining Whisper acoustic encoding and BERT text encoding with cross-attention fusion estimates emotion, depression, and pain, reaching a mean macro F1 of 0.652. The full system is implemented as a web application that can run entirely on consumer hardware, with no patient data transmitted to external services, supporting compliance with GDPR and KVKK.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.06110 — 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 2026-10-25T21:24:38.274Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).