arXiv cs.CL· Guangyuan Wang, Yifan Zhang, Shilong Liu·· 12 小时前AI 评分34
AIR：面向高效长程推理的自适应索引复用方法
When Should an Agent Refresh? Adaptive Index Reuse for Efficient Long-Horizon Reasoning
AI 导读
针对语言智能体长上下文推理中索引器每层重复打分的问题，研究者提出 Adaptive Index Reuse（AIR），按智能体轨迹分段学习刷新层数，由小型控制器依据已完成计算与最新工具事件从嵌套模式库中选择方案。
正文 · 原文
Abstract:Language agents read code, tool output, and dialogue in contexts that grow at every step. Dynamic sparse attention lets a small indexer choose the earlier tokens each query attends to, but the indexer still scores the whole prefix at every layer. Cross-layer reuse methods such as IndexCache rerun the indexer at only some layers, with one fixed pattern for every input. In an agent, the relevant evidence can change abruptly when a traceback or test result arrives, so fresh selections matter more at some steps than at others. We propose Adaptive Index Reuse (AIR), which keeps IndexCache's execution and learns, for each segment of an agent episode, how many layers refresh their selection. A small controller reads signals from completed computation and the latest tool event, chooses a pattern from a nested library, and learns from terminal task reward under an expected compute budget. On Qwen3-4B-Instruct-2507 with a 128K context, AIR improves success over the strongest static schedule at matched cost on SWE-bench Verified (27.0% to 32.4%), Terminal-Bench 2.0, and three $\tau^2$-bench domains, and it lowers time per successful task on all five. Across 50 backbone, context, and benchmark settings, it matches or exceeds that schedule in 44.
| Subjects: | Machine Learning (cs.LG); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.01429 [cs.LG] |
| (or arXiv:2611.01429v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01429 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Guangyuan Wang [view email]
[v1]
Sun, 1 Nov 2026 02:11:42 UTC (2,682 KB)
来源：arXiv cs.CL · arxiv.org