让AI只读关键信息，大幅减少token消耗和延迟
Read Less, Solve More: Token-Efficient Sparse Reading for AI Agents
- 用可训练的读取门控机制，提前过滤无关内容
- 在六种模型上降低92.9%的token用量，提速89%
- 无需重训，适配多种AI框架，适合长任务场景
长时序智能体依赖频繁访问外部资源，但现有读取接口常暴露完整内容，即使仅需零星证据。这种过度读取增加了token与延迟开销，还可能稀释任务相关信号。现有上下文压缩方法多在内容已进入轨迹后才干预。我们提出SparseRead——一种无需训练、模型透明的读取层，可在内容进入模型前控制其准入。SparseRead结合感知模式的读取门控、可扩展的读取后端及状态化协议，实现有界、来源锚定的证据获取，并支持显式精炼、验证、停止与回退。在包括Claude Opus 5在内的六种前沿模型和五个工作负载场景中，该方法最高降低92.9%的token量与89.0%的墙时时间，同时保持或提升任务质量。其在三种代理框架中的稳定表现进一步证明了广泛的兼容性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。