arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.07587cs.AIcs.CL
收藏

超越事实检索:具有生成语义工作区的RAG episodic记忆

Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces

Shreyas Rajesh, Pavan Holur, Chenda Duan, David Chong, Vwani Roychowdhury

AI总结:

GSW通过生成语义工作区提升LLM的长上下文推理能力,实现更高效的记忆管理与时空连贯性。

摘要:

大型语言模型(LLMs)在长上下文推理中面临根本性挑战:许多文档超过其有限的上下文窗口,而性能在适合的文本上会随着序列长度的增加而下降,需要借助外部记忆框架进行增强。当前的解决方案,从基于语义嵌入的检索发展到更复杂的结构化知识图谱表示,以提高感知和关联性,都是针对事实检索的,无法构建所需的空间-时间锚定的叙述表示,以跟踪通过事件的实体。为了弥合这一差距,我们提出了生成语义工作区(GSW),一种神经启发式的生成记忆框架,能够构建演进情境的结构化、可解释的表示,使LLMs能够对演进的角色、行动和时空上下文进行推理。我们的框架包括一个操作符,将输入观察映射到中间语义结构,以及一个调和器,将这些整合到一个持久的工作区中,强制时间、空间和逻辑的连贯性。在包含从10万到100万词长度的语料库的Episodic Memory Benchmark(EpBench)[huet_episodic_2025]上,GSW在现有基于RAG的基线基础上,表现提升高达20%。此外,GSW效率极高,比下一个最节省token的基线减少了51%的查询时间上下文token,大大降低了推理时间成本。更广泛地说,GSW为赋予LLMs类人记忆提供了具体蓝图,为能够对长时间跨度进行推理的更强大代理铺平了道路。代码可在https://github.com/roychowdhuryresearch/gsw-memory获取。

英文摘要:

Large Language Models (LLMs) face fundamental challenges in long-context reasoning: many documents exceed their finite context windows, while performance on texts that do fit degrades with sequence length, necessitating their augmentation with external memory frameworks. Current solutions, which have evolved from retrieval using semantic embeddings to more sophisticated structured knowledge graphs representations for improved sense-making and associativity, are tailored for fact-based retrieval and fail to build the space-time-anchored narrative representations required for tracking entities through episodic events. To bridge this gap, we propose the \textbf{Generative Semantic Workspace} (GSW), a neuro-inspired generative memory framework that builds structured, interpretable representations of evolving situations, enabling LLMs to reason over evolving roles, actions, and spatiotemporal contexts. Our framework comprises an \textit{Operator}, which maps incoming observations to intermediate semantic structures, and a \textit{Reconciler}, which integrates these into a persistent workspace that enforces temporal, spatial, and logical coherence. On the Episodic Memory Benchmark (EpBench) \cite{huet_episodic_2025} comprising corpora ranging from 100k to 1M tokens in length, GSW outperforms existing RAG based baselines by up to \textbf{20\%}. Furthermore, GSW is highly efficient, reducing query-time context tokens by \textbf{51\%} compared to the next most token-efficient baseline, reducing inference time costs considerably. More broadly, GSW offers a concrete blueprint for endowing LLMs with human-like episodic memory, paving the way for more capable agents that can reason over long horizons. Code is available at https://github.com/roychowdhuryresearch/gsw-memory.

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。

↑