HRD-BioAgent: Evidence-Grounded Agentic Reasoning for Multimodal Homologous Recombination Deficiency Prediction

Homologous recombination deficiency (HRD) is commonly characterized by genomic scars, but its phenotype is also reflected across mutation, transcriptomic, epigenetic, and histomorphologic modalities. Conventional multimodal predictors can estimate HRD status, yet they provide limited support for reasoning about whether biological evidence is consistent with a patient-level prediction, particularly when definitive genomic measurements are unavailable. We introduce HRD-BioAgent, an evidence-grounded agentic framework that combines multimodal HRD prediction with adaptive biological evidence acquisition. HRD-BioAgent organizes modality-specific signatures in a provenance-aware HRD Evidence Map and uses a ReAct workflow to determine when additional genomic evidence is needed. For a patient requiring additional evidence, the agent can invoke a genomic analysis tool to derive SBS3 mutation-signature evidence from raw trinucleotide mutation profiles, while numerical predictions are produced by a calibrated fold-local meta-model rather than an LLM. We separate the value of the evidence that is integrated from the policy that decides when to acquire it. Under an "acquire-all" reference policy, in which every patient receives the complete evidence set, the evidence-integration model reaches AUROC 0.923 on TCGA-BRCA ($N=958$); on a matched complete-case subset ($N=616$), adding SBS3 to a non-agent OOF stacking baseline raises AUROC from 0.878 to 0.906 (two-sided paired-bootstrap $p=0.0008$), and integrating the complete evidence set reaches 0.916, a further numerical increment that is not statistically distinguishable from chance under two-sided testing ($\Delta$AUROC $=0.009$, $p=0.068$). The paper's contribution therefore rests on SBS3 retrieval, provenance, and auditable concordance rather than on this increment. A "confidence-gated adaptive" policy that requests additional evidence only for patients whose prediction remains uncertain retains AUROC 0.907 against an acquire-all reference of 0.919 on the same cohort ($N=898$) while scheduling 58% fewer evidence-analysis steps. HRD-BioAgent also provides patient-level reasoning traces, provenance, and prediction-evidence concordance, enabling auditable HRD prediction under incomplete multimodal measurements.