PRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making

Ziyang Ling; Shuyu Lu; Ziyi Chen

cs.CLOct 14, 2026

PRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making

Authors: Ziyang Ling, Shuyu Lu, Ziyi Chen

Organizations: University of Science and Technology of China, Hefei, China · The University of Texas Health Science Center at Houston, Houston, United States

Abstract

Medical prescribing errors for multimorbid patients, who require complex drug regimens, are a major patient safety concern. These errors often stem from fragmented decision-making across medical specialties, a critical coordination failure that leads to adverse drug events and rehospitalizations. To address this coordination challenge, we introduce PRISMATIC, a multi-agent architecture where specialized agents, each representing a workflow role, collaboratively generate and refine treatment plans. Operating on a blackboard architecture, the system first structures patient information from clinical notes, then iteratively develops safe, rational, and interpretable drug regimens. The agents' collaboration is governed by two novel adaptive coordination mechanisms: (1) Dynamic Self-Updating Weight Adjustment (DSWA), a long-term mechanism that adjusts the influence weights of agents based on historical case outcomes, enabling the system to adapt and trust more reliable specialists over time. (2) Discrepancy Feedback Precise Calibration (DFPC), a short-term mechanism where agents provide iterative feedback to resolve disagreements and eliminate prescription conflicts for the current patient. Experiments on patient records from the MIMIC-IV database show that PRISMATIC significantly reduces drug conflicts, improves prescription coverage, and enhances treatment consistency compared to strong LLM baselines. Our work demonstrates that structuring clinical co-treatment as a multi-agent coordination problem offers a promising path toward safer and more coherent multidisease management.

Figures & tables

Figure 1. For patients with complex conditions and multiple comorbidities, conflicts and omissions may arise due to drug interactions and physician cognitive load. In contrast, PRISMATIC is a safe, comprehensive, and rational clinical prescription decision support system application. LLM vs. \textbf{\texttt{PRISMATIC}} Prescription — Figure 1. For patients with complex conditions and multiple comorbidities, conflicts and omissions may arise due to drug interactions and physician cognitive load. In contrast, PRISMATIC is a safe, comprehensive, and rational clinical prescription decision support system application. LLM vs. **`PRISMATIC`** Prescription

Figure 2. Multimorbid patients often experience medication conflicts and pharmacological omissions in real-world prescribing due to fragmented care and incomplete analysis of complex information. multimorbid patient

Agent	Core Responsibility	Key Function in the Coordination Process
Information Analysis (IA)	Structure the Input	Establishes the common ground for collaboration by parsing raw clinical text (T) into a structured, shared representation (Chief Complaint ( CP ), Patient Information ( PI ) on the blackboard.
Prescription Generation (PG)	Propose a Solution	Acts as the primary reasoner. Synthesizes the structured information {CP, PI, OI} and contextual information from the blackboard to generate an initial candidate prescription ( $\textit{P}_{n}$ ). The prescription is then iteratively negotiated with the SC, PR, and EA agents through the inner loop ( DFPC ), undergoing refinement based on their feedback until a consensus is reached.
Safety Check (SC)	Critique on Safety	Functions as a specialized critic targeting the Safety Objective. Verifies the candidate prescription against formal safety constraints ( DDI, DPI, Dosage ) 1 1 1 Formally, the safety checks correspond to satisfying the constraints: $\forall\,i\neq j:\textbf{DDI}_{P}(d_{i},d_{j})=0$ ; $\forall\,i:\textbf{DPI}_{P}(d_{i},\textbf{PI}_{n})=0$ ; and ensuring dosage $u_{i}\in[u^{min}_{i},u^{max}_{i}]$ . and posts specific, actionable violations for collective resolution.
Pharm. Rationality (PR)	Critique on Rationality	Functions as a specialized critic targeting the Rationality Objective. Evaluates the prescription’s therapeutic Coverage and Duplication 2 2 2 The rationality objective is formalized as maximizing coverage, where ideally $\forall cp\in\textbf{CP}$ , $\exists d_{i}\in\textbf{D}$ s.t. $d_{i}\mapsto cp$ while ensuring zero duplication, $\forall i\neq j$ , $Indication(d_{i})\neq Indication(d_{j})$ for the same complaint. to ensure clinical efficacy and efficiency, posting its findings as feedback.
Evaluation Agent (EA)	Adjudicate & Decide	Serves as the coordinator and adjudicator of the inner loop. It aggregates critiques from SC and PR , assesses interpretability, and computes a unified score to decide whether to accept the prescription or trigger a refinement cycle via DFPC .
Reflection & Feedback (RF)	Drive Long-Term Learning	Functions as the organizational learning facilitator. It compares the final prescription $\mathbf{P}_{\textnormal{final}}$ to a gold standard $\mathbf{P}_{\textnormal{gold}}$ to generate the discrepancy signal that drives the long-term adaptation of the entire system via the DSWA outer loop.

Table 1. The PRISMATIC Agent Society: Roles and Responsibilities in the Coordination Process

Figure 3. Complete workflow of PRISMATIC workflow

\bar{r}_{i}^{(t)}\leftarrow(1-\gamma)\bar{r}_{i}^{(t-1)}+\gamma r_{i}^{(t)}

Algorithm 1 Dynamic Self-updating Weight Adjustment (DSWA)

		Complexity i(%)				Complexity ii(%)				Complexity iii(%)				Complete Dataset(%)
Method	Model	OR	Prec.	EM	ZIR	OR	Prec.	EM	ZIR	OR	Prec.	EM	ZIR	OR	Prec.	EM	ZIR
Zero-Shot	GPT-4o	45.87	51.89	4.08	95.24	35.20	36.89	2.37	93.01	15.35	19.35	0.34	81.47	29.11	25.72	2.05	89.13
	Qwen-3	41.12	44.46	4.01	95.31	32.45	38.90	0.99	92.40	16.09	20.12	0.43	81.80	21.56	28.78	1.60	89.08
	DeepSeek-R1	47.23	48.06	10.20	94.43	39.13	37.02	1.27	93.06	17.89	14.01	0.43	78.74	31.48	25.20	3.39	87.87
	LLaMA3.1	45.10	43.29	6.05	94.49	29.11	31.78	1.60	91.19	13.90	19.91	0.10	79.74	32.45	36.40	2.23	87.65
Few-Shot	GPT-4o	44.23	58.91	7.27	95.92	29.09	31.98	1.38	93.06	19.89	20.11	0.29	86.78	31.61	29.09	2.57	91.40

Table 2. Comparison of performance of mainstream large models in medical question-answering tasks under different complexity levels. Complexity

i

iii

represents simple to complicated tasks. This table summarizes the performance of four models under various strategies and SFT medical models. Bold values indicate the best performance for each complexity level. Underline values indicates the second-best performance for each complexity.

Figure 4. Heatmap of precision across varying chronic disease and prescription complexities. heatmap complexity

Component	OR	Prec.	EM	ZIR
w/o IA	52.43	59.34	11.98	93.43
w/o SC	41.25	50.22	10.56	78.98
w/o PR	44.13	49.65	9.33	82.91
w/o DSWA	48.55	55.11	8.56	91.23
w/o DFPC	49.56	59.22	7.42	89.35
w/o EA	54.90	67.23	12.78	95.09

Table 3. Ablation study results for the PRISMATIC model with GPT-4o across various components. Bold values indicate the validity of PRISMATIC .

Figure 5. Evolution of risk weights across six dimensions in the DSWA mechanism. Every 500 cases per iteration round. The line graph illustrates how weights dynamically adjust over time. DSWA weight change.

Drug-Drug Interaction Prediction

See all 14 papers

May 25, 2026

Multi-Agent Coordination Adaptation via Structure-Guided Orchestration

As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptability becomes increasingly challenging. Existing systems typically adopt either structure-centric methods, committing to structures determined upfront that limit fine-grained control, or orchestration-centric methods, adapting decisions dynamically while leaving coordination structure implicit and unstable. To address this challenge, we revisit multi-agent coordination from a probabilistic perspective, casting it as posterior inference over the joint distribution of structure and orchestration. We introduce MACA, an automated coordination framework that learns a task- and budget-conditioned structural prior over agent participation and interactions. This prior guides a policy-based orchestration as an approximation to posterior inference, enabling efficient solutions with fine-grained control. Across benchmarks, MACA outperforms adaptive multi-agent baselines by an average of 8.42% while using 43.19% fewer tokens. Further investigation reveals that joint adaptation of structure and orchestration suppresses redundant interactions, converging coordination toward task-effective execution.

Haoran Li, Shulun Chen, Shaoyuan Sun +1

Nanjing University · University of Technology Sydney, Sydney, Australia · University of New South Wales, Sydney, Australia

Multi-Agent LLM Systems Multi-Agent System Optimization Multi-Agent Coordination Multi-Agent Orchestration LLM Agent Orchestration

Ask PDF

Mar 1, 2026

MedCollab: IBIS-Guided Multi-Agent Collaboration with Hierarchical Disease Relation Chains for Clinical Diagnosis

Clinical diagnosis is a gradual process of evidence integration, in which physicians move from symptoms and medical history to examinations, competing hypotheses, disease relations, and treatment decisions. Large language models have advanced medical text understanding and generation. Yet their clinical use remains limited by weak evidence grounding, opaque reasoning, and inconsistent links among differential diagnosis, final diagnosis, diagnostic basis, and treatment planning. We introduce MedCollab, a multi-agent framework for full-cycle clinical diagnosis and report generation. MedCollab coordinates specialist and examination agents according to patient records. It structures agent deliberation with an Issue-Based Information System (IBIS) protocol, so that each diagnostic position is supported by patient-specific evidence and medical knowledge. It also builds Hierarchical Disease Relation Chains (HDRC) to connect accepted hypotheses through progression, complication, and comorbidity relations. During multi-round deliberation, a verifier-guided consensus module evaluates evidence support, medical plausibility, and logical conflicts. It then adjusts agent contributions and filters unsupported reasoning. Experiments on ClinicalBench and MIMIC-IV show that MedCollab outperforms leading LLMs and medical multi-agent baselines in diagnostic accuracy, evidence consistency, and clinical reasoning quality. These results indicate that structured and auditable collaboration can produce more faithful and clinically coherent diagnostic reports.

Yuqi Zhan, Xinyue Wu, Tianyu Lin +6

Hangzhou Dianzi University · Zhejiang University · Children’s Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Children and Adolescents’ Health and Diseases

Multi-Agent LLM Systems Medical Report Generation Healthcare Medical Diagnosis Multi-Agent Debate Clinical Reasoning+1

Ask PDF

May 27, 2026

SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication Recommendation

Medication recommendation predicts medications for patient visits, but existing methods still face two key challenges. At the model level, traditional drug recommendation methods only predict structured drug codes with limited evidence grounding, while LLM agents can use richer clinical context but may lack safety verification and traceability. At the task level, existing benchmarks often use broad medication categories, which ignore subgroup-level safety differences and can lead to risk overestimation. We introduce the first fine-grained medication recommendation setting based on fourth-level ATC code generation. We propose Safe Prescription Agent (SafeRx-Agent), a knowledge-grounded multi-agent framework that uses patient context, external clinical knowledge, and safety verification to recommend traceable medication sets. Experimental results on MIMIC-III and MIMIC-IV datasets show that SafeRx-Agent improves fine-grained medication prediction accuracy while controlling drug interactions, contraindications, and medication set size.

Xinyu Wang, Hanwei Wu, Zhenghan Tai +7

McGill University · McMaster University · University of Toronto +1

Medication Recommendation Multi-Agent LLM Systems Drug-Drug Interaction Prediction Healthcare Clinical Decision Support LLM Agent Safety

Ask PDF

Abstract

Drug-Drug Interaction Prediction

Explore similar work

Multi-Agent Coordination Adaptation via Structure-Guided Orchestration

MedCollab: IBIS-Guided Multi-Agent Collaboration with Hierarchical Disease Relation Chains for Clinical Diagnosis

SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication Recommendation