Preprint
Aug 2026
Read Less, Solve More: Token-Efficient Sparse Reading for AI Agents
Long-horizon agents increasingly rely on repeated access to external artifacts, yet current reading interfaces often expose entire objects even when only sparse evidence is needed. This over-reading increases token and latency costs and can dilute task-relevant evidence, while existing context-reduction methods mainly...
Ze-Dong Liu, Jiaan Wu, Xin-Yang Ma et al.
· 0 citations