Index-free search beats ReAct on evidence recall 84.8% to 50.4% — no embeddings, no preprocessing, works on documents that change

arXiv 2608.16185·medium signalXBlueskyLinkedInCopy link

LENS maintains a query-conditioned belief over candidate text units and refines it with three proposal strategies (lexical match, local scan, exploratory jump), using the LLM itself as a relevance oracle within a fixed compute budget. It reached 62.4% exact match with 84.8% evidence recall against a ReAct baseline's 50.4% recall; on unindexed Wikipedia it matched EM (43.3% vs 42.7%) while grounding far more answers in retrieved evidence (84.0% vs 70.7%). For builders, this is a credible option for corpora too volatile to index — the retrieval quality gap shows up in grounding, not headline accuracy.