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 2604.20117cs.CL
收藏

知即建构:基于模式约束的代理记忆生成

To Know is to Construct: Schema-Constrained Generation for Agent Memory

UnionPay(中国银联)

Lei Zheng, Weinan Song, Daili Li, Yanming Yang

AI总结:

本文提出SCG-MEM架构,通过模式约束生成实现记忆检索,避免结构幻觉并提升多跳推理能力,实验显示其在LoCoMo基准上表现优异。

摘要:

建构主义认识论认为知识是主动建构而非被动复制。尽管大型语言模型(LLMs)具有生成性,但现有代理记忆系统仍基于密集检索。然而,密集检索依赖于句子内的语义重叠或实体匹配,导致嵌入无法区分语义相似但上下文不同的实例,引入大量噪声。相反,直接使用开放式生成进行记忆访问会引发

英文摘要:

Constructivist epistemology argues that knowledge is actively constructed rather than passively copied. Despite the generative nature of Large Language Models (LLMs), most existing agent memory systems are still based on dense retrieval. However, dense retrieval heavily relies on semantic overlap or entity matching within sentences. Consequently, embeddings often fail to distinguish instances that are semantically similar but contextually distinct, introducing substantial noise by retrieving context-mismatched entries. Conversely, directly employing open-ended generation for memory access risks "Structural Hallucination" where the model generates memory keys that do not exist in the memory, leading to lookup failures. Inspired by this epistemology, we posit that memory is fundamentally organized by cognitive schemas, and valid recall must be a generative process performed within these schematic structures. To realize this, we propose SCG-MEM, a schema-constrained generative memory architecture. SCG-MEM reformulates memory access as Schema-Constrained Generation. By maintaining a dynamic Cognitive Schema, we strictly constrain LLM decoding to generate only valid memory entry keys, providing a formal guarantee against structural hallucinations. To support long-term adaptation, we model memory updates via assimilation (grounding inputs into existing schemas) and accommodation (expanding schemas with novel concepts). Furthermore, we construct an Associative Graph to enable multi-hop reasoning through activation propagation. Experiments on the LoCoMo benchmark show that SCG-MEM substantially improves performance across all categories over retrieval-based baselines.

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。

↑