TheraAgent: Multi-Agent Framework with Self-Evolving Memory and Evidence-Calibrated Reasoning for PET Theranostics

2026-03-13

AI Summary

This study addresses the challenge of predicting treatment response to 177Lu-PSMA radioligand therapy in patients with metastatic castration-resistant prostate cancer (mCRPC) by proposing the first multi-agent framework tailored for PET-based theranostics. The approach tackles three key challenges: data scarcity, multi-source heterogeneous data integration, and model hallucination. It leverages a multi-expert confidence-weighted consensus mechanism, a self-evolving agent memory (SEA-Mem), and evidence-calibrated reasoning grounded in findings from the VISION and TheraP trials. By integrating uncertainty quantification, case-based memory learning, and an evidence-based knowledge base, the method achieves reliable predictions under limited data conditions, demonstrating 75.7% accuracy on a real-world cohort of 35 patients and 87.0% accuracy on 400 synthetic cases—significantly outperforming existing medical AI agent approaches.

Technology Category

• Multiagent Systems: Multiagent Systems under Uncertainty
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

PET theranostics is transforming precision oncology, yet treatment response varies substantially; many patients receiving 177Lu-PSMA radioligand therapy (RLT) for metastatic castration-resistant prostate cancer (mCRPC) fail to respond, demanding reliable pre-therapy prediction. While LLM-based agents have shown remarkable potential in complex medical diagnosis, their application to PET theranostic outcome prediction remains unexplored, which faces three key challenges: (1) data and knowledge scarcity: RLT was only FDA-approved in 2022, yielding few training cases and insufficient domain knowledge in general LLMs; (2) heterogeneous information integration: robust prediction hinges on structured knowledge extraction from PET/CT, laboratory tests, and free-text clinical documentation; (3) evidence-grounded reasoning: clinical decisions must be anchored in trial evidence rather than LLM hallucinations. In this paper, we present TheraAgent, to our knowledge, the first agentic framework for PET theranostics, with three core innovations: (1) Multi-Expert Feature Extraction with Confidence-Weighted Consensus, where three specialized experts process heterogeneous inputs with uncertainty quantification; (2) Self-Evolving Agentic Memory (SEA-Mem), which learns prognostic patterns from accumulated cases, enabling case-based reasoning from limited data; (3) Evidence-Calibrated Reasoning, integrating a curated theranostics knowledge base to ground predictions in VISION/TheraP trial evidence. Evaluated on 35 real patients and 400 synthetic cases, TheraAgent achieves 75.7% overall accuracy on real patients and 87.0% on synthetic cases, outperforming MDAgents and MedAgent-Pro by over 20%. These results highlight a promising blueprint for trustworthy AI agents in PET theranostics, enabling trial-calibrated, multi-source decision support. Code will be released upon acceptance.

Problem

• PET theranostics
• treatment response prediction
• heterogeneous data integration
• evidence-based reasoning
• data scarcity

Innovation

• Multi-Agent Framework
• Self-Evolving Memory
• Evidence-Calibrated Reasoning
• PET Theranostics
• Confidence-Weighted Consensus