少读多解：面向智能体的令牌高效稀疏阅读
Read Less, Solve More: Token-Efficient Sparse Reading for AI Agents
浏览论文内容
中文总结 AI 辅助
针对智能体过度阅读导致的成本高、证据稀释问题，提出无需训练的SparseRead阅读层，可减少92.9%令牌量、89.0%耗时，且在多模型、多场景下保持或提升任务质量，可移植性强。
中文摘要 AI 辅助
长程智能体日益依赖对外部制品的重复访问，然而当前阅读接口往往会暴露完整对象，即便仅需稀疏证据。这种过度阅读会增加令牌数与延迟成本，还可能稀释任务相关证据，而现有上下文缩减方法主要在大量内容已进入轨迹后才介入。我们提出SparseRead，这是一种无需训练、模型透明的阅读层，可在不必要证据到达模型上下文前控制内容准入。SparseRead结合了感知机制的阅读门、可扩展的阅读后端，以及带显式细化、验证、停止和回退的有状态协议，用于获取受边界约束、锚定源的证据。在包括Claude Opus 5在内的六种前沿模型和五种工作负载场景中，SparseRead最多可减少92.9%的令牌量和89.0%的墙钟时间，同时保持或提升任务质量。其在三种智能体框架上的一致增益进一步证明了广泛的可移植性。
英文摘要
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 intervene after broad content has already entered the trajectory. We present SparseRead, a training-free, model-transparent reading layer that controls content admission before unnecessary evidence reaches the model context. SparseRead combines a regime-aware Read Gate, extensible Reader Backends, and a stateful protocol for bounded, source-anchored evidence acquisition with explicit refinement, verification, stopping, and fallback. Across six frontier models, including Claude Opus 5, and five workload scenarios, SparseRead reduces token volume by up to 92.9% and wall time by up to 89.0%, while preserving or improving task quality. Its consistent gains across three agent frameworks further demonstrate broad portability.
