用持久化助手减少重复搜索，让编程机器人更省电。
Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems
- 引入持久化搜索代理记录历史，避免多智能体重复探索同一代码区。
- 在真实任务中降低11%至30%的显卡能耗，性能不变。
- 适合关注AI编程系统能效与可持续性的研究者和开发者。
多智能体系统（MAS）显著推动了自主软件工程（SWE）发展，但其日益增长的推理能耗引发可持续性担忧。本文发现，能耗主要集中在被忽视的冗余输出标记上：实验表明，单个输出标记的能耗是输入或缓存标记的30至1,000倍；同时，智能体反复探索重叠的代码库区域导致每轮任务输出量激增。为此，我们提出Librarian——一个持久化的搜索子代理，通过追踪代码库搜索历史，抑制各智能体间的冗余探索行为。它不返回完整文件片段，而是提供指向文件区域的简短引用，进一步压缩输出标记数量。在SWE-Bench Verified与SWE-Bench-Live数据集上，Librarian使现有MAS系统的每轮任务GPU能耗降低11%至30%，同时保持任务性能不变。代码已开源：https://github.com/ml-postech/Librarian。
原文摘要 · Abstract (English)
Multi-agent systems (MAS) have substantially advanced autonomous software engineering (SWE), but their growing inference energy demands raise sustainability concerns. In this paper, we demonstrate that this cost is concentrated in an overlooked source: redundant output tokens generated across agents. Two empirical findings ground this claim. First, our per-token energy attribution for MAS reveals a sharp asymmetry: an output token consumes 30 to 1,000 times more energy than an input or cached token. Second, MAS inflate per-episode output because agents repeatedly re-explore overlapping repository regions. To address this inefficiency, we propose Librarian, a persistent search sub-agent that tracks repository-search history and suppresses redundant exploration actions across agents. By returning short references to file regions instead of full file excerpts, Librarian further reduces output-token volume. On SWE-Bench Verified and SWE-Bench-Live, Librarian reduces per-episode GPU energy consumption of existing multi-agent SWE systems by 11 to 30% while preserving task performance. Our code is available at https://github.com/ml-postech/Librarian.
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。