Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)
Summary
This paper presents a reinforcement learning post-training pipeline for tool-calling LLM agents operating on FHIR healthcare data, achieving a 77% answer correctness on FHIR-AgentBench using a smaller Qwen3-8B model compared to 50% with o4-mini.
View Cached Full Text
Cached at: 05/15/26, 06:27 AM
# Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR) Source: [https://arxiv.org/abs/2605.14126](https://arxiv.org/abs/2605.14126) [View PDF](https://arxiv.org/pdf/2605.14126) > 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\. ## Submission history From: Marius Knorr \[[view email](https://arxiv.org/show-email/3c34a810/2605.14126)\] **\[v1\]**Wed, 13 May 2026 21:27:21 UTC \(1,359 KB\)
Similar Articles
World Feedback for Clinical Agents: Diagnosing RL in FHIR Environments
This paper examines the use of reinforcement learning from world feedback for clinical protocol-execution tasks in FHIR environments, identifies structural barriers like high silent-finish ceilings and zero-gradient tasks, and introduces MedAgentBench-v3 with a lower ceiling. It shows that pure RL underperforms rule-based SFT due to these barriers, and proposes a combined SFT+RL approach.
CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward
CacheRL trains small agent foundation models for multi-step tool-calling tasks, achieving 92% process accuracy (approaching GPT-5's 94%) with 100x less compute using cached rollouts and hybrid reward shaping, with innovations in knowledge transfer, cache-aware rewards, and iterative SFT/GRPO training.
Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning
This paper proposes TRUST, a method that integrates uncertainty quantification into reinforcement learning reward design to improve LLM agents' tool-calling decisions, enhancing decision quality and maintaining reliable uncertainty estimates.
From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b
This paper presents a question-type-specific LLM framework for the BioASQ 14b Task B biomedical QA challenge, using different inference strategies (snippet shuffling, chain-of-thought, multi-agent collaboration) for yes/no, factoid, and list questions, achieving competitive results including first place in the factoid subtask of Batch 4.
Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows
This paper presents a proof-of-concept using Reinforcement Learning with Verifiable Rewards (RLVR) to train small language models for tool-use in enterprise SaaS workflows like Jira and Confluence. The approach uses synthetic environments and GRPO training to improve tool-call accuracy, achieving significant reward gains over baselines.