The Decision Value of Inferred Structure in Budgeted Evidence Acquisition

Model-inferred structures guide which evidence a retrieval-augmented system reads under a limited budget. When these structures omit useful evidence, the effect on answer quality may depend on whether later reading can recover it. We investigate this relationship through controlled comparisons on MuSiQue, starting from identical evidence states and independently varying structure and passage selection. We introduce structural defects by removing unread supporting passages from the structure while keeping them in the candidate pool. On affected states in a confirmation experiment using new source components, the same defect reduces answer F1 by $0.22$ with a lexical selector and $0.01$ with a strong model selector. This asymmetry persists with a second model endpoint and with 100-passage retrieved pools. On a sealed split of 1,668 questions, opened once for the final evaluation, the same defect reduces F1 by $0.21$ with the lexical selector and $0.01$ with the model selector, and structure changes the model selector's F1 by $-0.01$ (within $\pm 0.03$). The model selector more often finds the omitted evidence after returning to the full candidate pool. Structure improves the lexical selector but adds little to the strong model selector ($+0.004$, bounded within $\pm 0.03$), and none of the tested reliability-based controllers reliably outperforms using the strong selector throughout. Across MuSiQue and 2WikiMultihopQA, structure-free policies also remain on the quality–cost frontier at every tested budget. These findings identify fallback recovery as a key factor in the cost of structural defects and show that the benefit of explicit structure depends on the selector used.