Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval

• URL: http://arxiv.org/abs/2511.13293v1
• Date: Mon, 17 Nov 2025 12:15:46 GMT
• Title: Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval
• Authors: Chuang Zhao, Hui Tang, Hongke Zhao, Xiaofang Zhou, Xiaomeng Li,
• Abstract summary: Large language models (LLMs) offer a promising path to enhance healthcare predictions by drawing on their rich parametric knowledge.<n>LLMs are prone to factual inaccuracies due to limitations in the reliability and coverage of their embedded knowledge.<n>We propose GHAR, a underlinegenerative underlinehierarchical underlineagentic underlineRAG framework that simultaneously resolves when to retrieve and how to optimize the collaboration between submodules in healthcare.
• Score: 29.377256313893934
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate healthcare prediction is critical for improving patient outcomes and reducing operational costs. Bolstered by growing reasoning capabilities, large language models (LLMs) offer a promising path to enhance healthcare predictions by drawing on their rich parametric knowledge. However, LLMs are prone to factual inaccuracies due to limitations in the reliability and coverage of their embedded knowledge. While retrieval-augmented generation (RAG) frameworks, such as GraphRAG and its variants, have been proposed to mitigate these issues by incorporating external knowledge, they face two key challenges in the healthcare scenario: (1) identifying the clinical necessity to activate the retrieval mechanism, and (2) achieving synergy between the retriever and the generator to craft contextually appropriate retrievals. To address these challenges, we propose GHAR, a \underline{g}enerative \underline{h}ierarchical \underline{a}gentic \underline{R}AG framework that simultaneously resolves when to retrieve and how to optimize the collaboration between submodules in healthcare. Specifically, for the first challenge, we design a dual-agent architecture comprising Agent-Top and Agent-Low. Agent-Top acts as the primary physician, iteratively deciding whether to rely on parametric knowledge or to initiate retrieval, while Agent-Low acts as the consulting service, summarising all task-relevant knowledge once retrieval was triggered. To tackle the second challenge, we innovatively unify the optimization of both agents within a formal Markov Decision Process, designing diverse rewards to align their shared goal of accurate prediction while preserving their distinct roles. Extensive experiments on three benchmark datasets across three popular tasks demonstrate our superiority over state-of-the-art baselines, highlighting the potential of hierarchical agentic RAG in advancing healthcare systems.

Related papers

• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
  We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
  arXiv  Detail & Related papers  (2025-10-24T02:11:05Z)
• Towards Self-Evolving Benchmarks: Synthesizing Agent Trajectories via Test-Time Exploration under Validate-by-Reproduce Paradigm [60.36837655498119]
  We propose a Trajectory-based validated-by-Reproducing Agent-benchmark Complexity Evolution framework.<n>This framework takes an original task from an existing benchmark and encourages agents to evolve it into a new task with higher difficulty.<n>Experiments on the GAIA benchmark demonstrate that the TRACE framework consistently enhances task complexity while improving the reliability of correctness.
  arXiv  Detail & Related papers  (2025-10-01T01:52:52Z)
• RAR$^2$: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval [25.425621641226815]
  Large Language Models (LLMs) have shown promising performance on diverse medical benchmarks.<n>RAG has emerged as a key approach for mitigating knowledge gaps and hallucinations by incorporating external medical information.<n>We propose RAR$2$, a joint learning framework that improves Reasoning-Augmented Retrieval and Retrieval-Augmented Reasoning.
  arXiv  Detail & Related papers  (2025-09-24T05:35:57Z)
• Enhancing Retrieval Augmentation via Adversarial Collaboration [50.117273835877334]
  We propose the Adrial Collaboration RAG (AC-RAG) framework to address "Retrieval Hallucinations"<n>AC-RAG employs two heterogeneous agents: a generalist Detector that identifies knowledge gaps, and a domain-specialized Resolver that provides precise solutions.<n>Experiments show that AC-RAG significantly improves retrieval accuracy and outperforms state-of-the-art RAG methods across various vertical domains.
  arXiv  Detail & Related papers  (2025-09-18T08:54:20Z)
• MedSeqFT: Sequential Fine-tuning Foundation Models for 3D Medical Image Segmentation [55.37355146924576]
  MedSeqFT is a sequential fine-tuning framework for medical image analysis.<n>It adapts pre-trained models to new tasks while refining their representational capacity.<n>It consistently outperforms state-of-the-art fine-tuning strategies.
  arXiv  Detail & Related papers  (2025-09-07T15:22:53Z)
• Inference Gap in Domain Expertise and Machine Intelligence in Named Entity Recognition: Creation of and Insights from a Substance Use-related Dataset [6.343399421398501]
  Nonmedical opioid use is an urgent public health challenge.<n>We present a named entity recognition (NER) framework to extract two categories of self-reported consequences from social media narratives.<n>We evaluate both fine-tuned encoder-based models and state-of-the-art large language models (LLMs) under zero- and few-shot in-context learning settings.
  arXiv  Detail & Related papers  (2025-08-26T23:09:43Z)
• CardAIc-Agents: A Multimodal Framework with Hierarchical Adaptation for Cardiac Care Support [37.20545002349272]
  CardAIc-Agents is a framework to augment AI models with external tools and adaptively support diverse cardiac tasks.<n>A CardiacRAG agent generated general plans from updatable cardiac knowledge, while the chief agent integrated tools to autonomously execute these plans and deliver decisions.<n> Experiments across three datasets showed the efficiency of CardAIc-Agents compared to mainstream Vision-Language Models (VLMs), state-of-the-art agentic systems, and fine-tuned VLMs.
  arXiv  Detail & Related papers  (2025-08-18T16:17:12Z)
• MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph [57.54231831309079]
  We introduce MedKGent, a framework for constructing temporally evolving medical Knowledge Graphs.<n>We simulate the emergence of biomedical knowledge via a fine-grained daily time series.<n>The resulting KG contains 156,275 entities and 2,971,384 relational triples.
  arXiv  Detail & Related papers  (2025-08-17T15:14:03Z)
• Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA [17.823588070044217]
  We propose Discuss-RAG, a plug-and-play module designed to enhance the medical question answering system.<n>Our method introduces a summarizer agent that orchestrates a team of medical experts to emulate multi-turn brainstorming, thereby improving the relevance of retrieved content.<n> Experimental results on four benchmark medical QA datasets show that Discuss-RAG consistently outperforms MedRAG.
  arXiv  Detail & Related papers  (2025-04-30T01:37:44Z)
• SurgRAW: Multi-Agent Workflow with Chain-of-Thought Reasoning for Surgical Intelligence [16.584722724845182]
  Integration of Vision-Language Models in surgical intelligence is hindered by hallucinations, domain knowledge gaps, and limited understanding of task interdependencies.<n>We present SurgRAW, a CoT-driven multi-agent framework that delivers transparent, interpretable insights for most tasks in robotic-assisted surgery.
  arXiv  Detail & Related papers  (2025-03-13T11:23:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.