arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2601.06282cs.CLcs.AI
收藏

Amory：通过代理推理构建连贯的叙事驱动代理记忆

Amory: Building Coherent Narrative-Driven Agent Memory through Agentic Reasoning

University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Amazon（亚马逊）

Yue Zhou, Xiaobo Guo, Belhassen Bayar, Srinivasan H. Sengamedu

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

Amory通过增强代理推理构建连贯的叙事驱动记忆，提升长期对话代理的推理性能与响应效率。

摘要：

长期对话代理面临一个根本性的可扩展性挑战：随着交互时间的延长，反复处理整个对话历史变得计算上不可行。当前的方法试图通过记忆框架来解决这个问题，这些框架主要将对话碎片分割成孤立的嵌入或图表示，并以RAG风格检索相关的内容。虽然计算效率高，但这些方法往往对记忆形成处理得非常有限，无法捕捉人类记忆的细微差别和连贯性。我们引入了Amory，一种工作记忆框架，它通过在离线时间增强代理推理来主动构建结构化的记忆表示。Amory将对话碎片组织成事件叙事，通过动量进行记忆巩固，并将外围事实语义化为语义记忆。在检索时，系统利用基于连贯性的推理来处理叙事结构。在LOCOMO基准测试中评估，Amory在长期推理方面显著优于先前的最先进方法，其性能与完整上下文推理相当，同时将响应时间减少了50%。分析显示，动量感知的巩固显著提高了响应质量，而基于连贯性的检索相比基于嵌入的方法提供了更优越的记忆覆盖。

英文摘要：

Long-term conversational agents face a fundamental scalability challenge as interactions extend over time: repeatedly processing entire conversation histories becomes computationally prohibitive. Current approaches attempt to solve this through memory frameworks that predominantly fragment conversations into isolated embeddings or graph representations and retrieve relevant ones in a RAG style. While computationally efficient, these methods often treat memory formation minimally and fail to capture the subtlety and coherence of human memory. We introduce Amory, a working memory framework that actively constructs structured memory representations through enhancing agentic reasoning during offline time. Amory organizes conversational fragments into episodic narratives, consolidates memories with momentum, and semanticizes peripheral facts into semantic memory. At retrieval time, the system employs coherence-driven reasoning over narrative structures. Evaluated on the LOCOMO benchmark for long-term reasoning, Amory achieves considerable improvements over previous state-of-the-art, with performance comparable to full context reasoning while reducing response time by 50%. Analysis shows that momentum-aware consolidation significantly enhances response quality, while coherence-driven retrieval provides superior memory coverage compared to embedding-based approaches.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑