# Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents

**Authors:** Zedong Liu, Jiaan Wu, Xinyang Ma, Le Xu, Kai Wang, Yuanchao Hu, Dingwen Tao, Guangming Tan  
**Lab:** Institute of Computing Technology · **Published:** 6 Nov 2026 · **Upvotes:** 22  
**Links:** [arXiv](https://arxiv.org/abs/2608.22237) · [PDF](https://arxiv.org/pdf/2608.22237) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2608.22237.html)

## Key numbers

- **92.9%**: SparseRead reduces total tokens by up to 92.9% and wall time by up to 89.0%
- **89.0%**: SparseRead reduces total tokens by up to 92.9% and wall time by up to 89.0%
- **97%**: preserving or improving task quality in 97% settings

## Abstract

Web-facing AI agents repeatedly access webpages, documents, repositories, and tool responses, yet reading interfaces often expose entire objects when only sparse evidence is needed. This over-reading increases token and latency costs and can dilute relevant evidence. We present SparseRead, a reusable reading control layer that governs content admission without modifying the agent model. Its Read Intent Protocol tracks evolving needs and source coverage; Adaptive Reader Backends select how evidence is located and exposed; and the Budgeted Read Gate bounds cumulative raw exposure per episode with faithful full-view fallback. A unified Reader interface supports interchangeable evidence acquisition across heterogeneous resources. Across six models, including Claude Opus 5, and five scenarios, SparseRead reduces total tokens by up to 92.9% and wall time by up to 89.0%, preserving or improving task quality in 97% settings. On Web deep-search tasks, it reduces tokens by 31.0--43.0% and task completion time by 23.0--37.0%. Ablations validate the three designs, while integration with three agent frameworks demonstrates portability.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.