arXiv cs.CL· Peter Baile Chen, Geoffrey X. Yu, Xinming Liu, Samuel Madden, Dan Roth, Jacob Andreas, Doug Downey, Michael Cafarella·· 10 天前AI 评分32
ExperienceIndex：面向 AI 智能体的工件锚定记忆层
ExperienceIndex: Artifact-Grounded Memory
AI 导读
针对 AI 智能体缺乏工件级经验记忆的问题，研究者提出 ExperienceIndex，一种基于历史推理轨迹捕获并复用工件知识的经验层，存储单工件经验与工件对经验两种形式，并以轻量中间件方式通过经验检索引导智能体定位相关工件。在多种语料与不同搜索框架的智能体方案上，该方法将答案质量最高提升 11.0 分，在线美元成本最高降低 50.5%，并展现出跨任务泛化与教师-学生学习两项能力。
正文 · 原文
Abstract:Knowledge-intensive tasks require answering many questions by reasoning about a shared corpus of artifacts (e.g., court cases, or scientific literature). As humans interact with these corpora, they naturally accumulate experiential knowledge about artifacts, enabling them to quickly identify the complete set of relevant artifacts for each new task. However, existing AI agents lack appropriate memory solutions to build or reuse such artifact-grounded experience, leading to lower answer quality and higher online cost. Existing memory solutions extract and reuse information from prior task-solving traces, but they primarily focus on user preferences, factual attributes, or abstract reasoning patterns rather than persistent artifact-specific knowledge. We introduce ExperienceIndex, a novel experience layer for AI agents that captures and reuses knowledge about artifacts based on prior reasoning traces. ExperienceIndex stores two complementary forms of experience: (i) single-artifact experiences that summarize an artifact's contribution to prior tasks and (ii) artifact-pair experiences that encode structural relationships discovered during past reasoning. Integrated as lightweight middleware, ExperienceIndex uses an experience retrieval mechanism to guide agents toward the complete set of relevant artifacts for new tasks, improving both answer quality and efficiency. Across diverse corpora and agentic solutions with different search frameworks, ExperienceIndex delivers consistent gains, raising answer quality by up to 11.0 points and reducing online dollar cost by up to 50.5%. We further demonstrate two benefits: (i) cross-task generalization, where experiences accumulated from text-to-SQL tasks transfer to factoid QA tasks over the same artifact corpus, and (ii) teacher-student learning, where experiences from a stronger model enable a weaker model to reach comparable performance.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.10091 [cs.CL] |
| (or arXiv:2610.10091v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10091 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Peter Baile Chen [view email]
[v1]
Wed, 7 Oct 2026 13:50:33 UTC (483 KB)
来源：arXiv cs.CL · arxiv.org