AgentPM-RAG: Autonomous Healthcare Program Orchestration through Efficient RAG Decoding and Self-Organizing Agentic Intelligence

DOI

10.2991/978-94-6463-978-0_36How to use a DOI?

Keywords

Project Management; Retrieval-Augmented Generation; Agentic AI; Healthcare Projects; RAG Decoding; Autonomous Decision-Making

Abstract

The complexity of healthcare project and program management has never been as high as it is with the multi-dimensional regulatory constraints, asynchronous orchestration of stakeholders, stochastic resource allocation and dynamically changing clinical demands. Conventional deterministic project management paradigm has little flexibility in dynamic healthcare ecosystems whereby, implementation latencies directly translate to patient outcomes and operating efficacy. The proposed paper presents AgentPM-RAG, a system that radically reconsiders a Retrieval-Augmented Generation (RAG) approach to decoding with self-organizing agentic AI to plan autonomous projects within healthcare programs. Our strategy transforms intelligence in projects through deploying emergent reasoning agents that make use of multivariate predictive risk modeling, adaptive resource optimization, and live constraint satisfaction. The framework combines hierarchical knowledge graphs, temporal embeddings and contextual semantic retrieval where compressed encoding of chunky encodings up to 30-fold rapidity in time-to-first-token. Transformative improvements at an empirical scale have been validated over fifteen large scale healthcare implementations: 56% decrease in critical path delays, 42% improvement in resource utilization, 67% lessening of budget variance, 51% increasing stakeholder satisfaction and 48% decrease in coordination overhead.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Madhusudan Bangalore Nagaraja
PY  - 2025
DA  - 2025/12/31
TI  - AgentPM-RAG: Autonomous Healthcare Program Orchestration through Efficient RAG Decoding and Self-Organizing Agentic Intelligence
BT  - Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
PB  - Atlantis Press
SP  - 417
EP  - 430
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-978-0_36
DO  - 10.2991/978-94-6463-978-0_36
ID  - Nagaraja2025
ER  -