Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)

• URL: http://arxiv.org/abs/2605.14126v1
• Date: Wed, 13 May 2026 21:27:21 GMT
• Title: Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)
• Abstract summary: We implement a multi-turn Code agent and post-train it with reinforcement learning using a custom harness and tools.<n>Our approach improves answer correctness from 50% (o4-mini) to 77% on FHIR-AgentBench using a smaller and cheaper Qwen3-8B model.
• Score: 0.4635383898871528
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fast Healthcare Interoperability Resources (FHIR) is the dominant standard for interoperable exchange of healthcare data. In FHIR, electronic health records form a directed graph of resources. Answering clinically meaningful questions over FHIR requires agents to perform multi-step reasoning, filtering, and aggregation across multiple resource types. Prior work shows that even tool-augmented LLM agents (retrieval, code execution, multi-turn planning) often select the wrong resources or violate traversal constraints. We study this problem in the context of FHIR-AgentBench, a benchmark for realistic question answering over real-world hospital data, and frame reasoning on FHIR as a sequential decision-making problem over a queryable structured graph. We implement a multi-turn CodeAct agent and post-train it with reinforcement learning using a custom harness and tools. A LLM Judge provides execution-grounded rewards. Compared to prompt-based, closed-model baselines, RL post-training improves performance while enforcing data-integrity constraints. Empirically, our approach improves answer correctness from 50% (o4-mini) to 77% on FHIR-AgentBench using a smaller and cheaper Qwen3-8B model. We present an end-to-end post-training pipeline (environment building, harness construction, model training and custom evaluation) that reliably improves multi-turn reasoning over structured clinical graphs.

Related papers

• RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases [49.47033473074821]
  We propose RelPrism, a multi-faceted self-supervised learning framework for RDBs.<n>RDB tasks often require multi-faceted information across different perspectives and granularities.<n>Our experiments show that RelPrism improves ROC-AUC by 4.15% for classification and reduces MAE by 10.75% for regression over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-22T05:19:58Z)
• ACC: Compiling Agent Trajectories for Long-Context Training [36.977301208747015]
  Agent Context Compilation converts trajectories from search, software engineering, and database querying agents into long-context QA pairs.<n>ACC is a simple but effective approach that can be combined with any existing long-context extension or training method.
  arXiv  Detail & Related papers  (2026-05-21T00:47:03Z)
• MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning [74.07254720088926]
  We introduce MM-Doc-R1, a novel framework that employs an agentic, vision-aware workflow to address long document visual question answering.<n>We propose Similarity-based Policy Optimization (SPO), addressing baseline estimation bias in existing multi-turn reinforcement learning (RL) algorithms like GRPO.<n>Our experiments on the MMLongbench-Doc benchmark show that MM-Doc-R1 outperforms previous baselines by 10.4%.
  arXiv  Detail & Related papers  (2026-04-15T07:39:08Z)
• Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models [78.68818219506313]
  This paper describes a multi-answer reinforcement learning approach for training LMs to perform distributional reasoning over multiple answers during inference.<n>Across question-answering, medical diagnostic, and coding benchmarks, we observe improved diversity, coverage, and set-level calibration scores compared to single answer trained baselines.
  arXiv  Detail & Related papers  (2026-03-25T22:20:25Z)
• Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction [0.18907108368038208]
  Current methods lack the adaptive policies needed to dynamically debug queries based on real-time execution feedback.<n>This paper introduces a novel agentic framework where an LLM learns a resilient policy for the sequential process of iterative SPARQL construction.<n>We show that a compact 3B- parameter model, trained exclusively via outcome-driven Reinforcement Learning (GRPO), can learn effective policies for this task.
  arXiv  Detail & Related papers  (2025-11-14T08:44:58Z)
• Stochastic Self-Organization in Multi-Agent Systems [28.70691568233268]
  Multi-agent systems (MAS) based on Large Language Models (LLMs) have the potential to solve tasks that are beyond the reach of any single LLM.<n>We introduce a response-conditioned framework that adapts communication on-the-fly.
  arXiv  Detail & Related papers  (2025-10-01T09:08:04Z)
• GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models [59.72897499248909]
  We propose a novel graph retriever trained end-to-end with Large Language Models (LLMs)<n>Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together.<n>Our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-20T02:38:00Z)
• FHIR-AgentBench: Benchmarking LLM Agents for Realistic Interoperable EHR Question Answering [17.141355981515012]
  Recent shift toward the Health Level Seven Fast Healthcare Resources (HL7 FHIR) standard opens a new frontier for clinical AI.<n>We introduce FHIR-AgentBench, a benchmark that grounds 2,931 real-world clinical questions in the HL7 FHIR standard.
  arXiv  Detail & Related papers  (2025-09-12T06:52:55Z)
• Reinforcing Question Answering Agents with Minimalist Policy Gradient Optimization [80.09112808413133]
  Mujica is a planner that decomposes questions into acyclic graph of subquestions and a worker that resolves questions via retrieval and reasoning.<n>MyGO is a novel reinforcement learning method that replaces traditional policy updates with gradient Likelihood Maximum Estimation.<n> Empirical results across multiple datasets demonstrate the effectiveness of MujicaMyGO in enhancing multi-hop QA performance.
  arXiv  Detail & Related papers  (2025-05-20T18:33:03Z)
• Offline Reinforcement Learning for LLM Multi-Step Reasoning [15.687002884103537]
  OREO (Offline Reasoning Optimization) is an offline reinforcement learning method for enhancing multi-step reasoning.<n>It reduces the need to collect pairwise data and enables better credit assignment.<n>It surpasses existing offline learning methods on multi-step reasoning benchmarks.
  arXiv  Detail & Related papers  (2024-12-20T18:49:45Z)
• MALT: Improving Reasoning with Multi-Agent LLM Training [67.76186488361685]
  MALT (Multi-Agent LLM Training) is a novel post-training strategy that divides the reasoning process into generation, verification, and refinement steps.<n>On MATH, GSM8K, and CSQA, MALT surpasses the same baseline LLM with a relative improvement of 15.66%, 7.42%, and 9.40% respectively.
  arXiv  Detail & Related papers  (2024-12-02T19:30:36Z)

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.