Structured Episodic Event Memory

2026-01-10 · Zhengxuan Lu, Dongfang Li, Yukun Shi, Beilun Wang, Longyue Wang, Baotian Hu arxiv

Current approaches to memory in Large Language Models (LLMs) predominantly rely on static Retrieval-Augmented Generation (RAG), which often results in scattered retrieval and fails to capture the structural dependencies required for complex reasoning. For autonomous agents, these passive and flat architectures lack the cognitive organization necessary to model the dynamic and associative nature of long-term interaction. To address this, we propose Structured Episodic Event Memory (SEEM), a hierarchical framework that synergizes a graph memory layer for relational facts with a dynamic episodic memory layer for narrative progression. Grounded in cognitive frame theory, SEEM transforms interaction streams into structured Episodic Event Frames (EEFs) anchored by precise provenance pointers. Furthermore, we introduce an agentic associative fusion and Reverse Provenance Expansion (RPE) mechanism to reconstruct coherent narrative contexts from fragmented evidence. Experimental results on the LoCoMo and LongMemEval benchmarks demonstrate that SEEM significantly outperforms baselines, enabling agents to maintain superior narrative coherence and logical consistency.

📄 PDF Abstract BibTeX arXiv:2601.06411

Code (0)

등록된 구현이 없습니다.

Episodic Memories Generation and Evaluation Benchmark for Large Language Models

2025-01-21 · Alexis Huet, Zied Ben Houidi, Dario Rossi

Episodic memory -- the ability to recall specific events grounded in time and space -- is a cornerstone of human cognition, enabling not only coherent storytelling, but also planning and decision-making. Despite their re…

Latent Structured Hopfield Network for Semantic Association and Retrieval

2025-06-02 · Chong Li, xiangyang xue, Jianfeng Feng, Taiping Zeng

Episodic memory enables humans to recall past experiences by associating semantic elements such as objects, locations, and time into coherent event representations. While large pretrained models have shown remarkable pro…

Decoder Retrieval

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

2025-11-10 · Shreyas Rajesh, Pavan Holur, Chenda Duan, David Chong 외 arxiv

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 …

Knowledge Graphs

CAST: Character-and-Scene Episodic Memory for Agents

2026-01-14 · Kexin Ma, Bojun Li, Yuhua Tang, Liting Sun 외 arxiv

Episodic memory is a central component of human memory, which refers to the ability to recall coherent events grounded in who, when, and where. However, most agent memory systems only emphasize semantic recall and treat …

Sequential memory improves sample and memory efficiency in Episodic Control

2021-12-29 · Ismael T. Freire, Adrián F. Amil, Paul F. M. J. Verschure

State of the art deep reinforcement learning algorithms are sample inefficient due to the large number of episodes they require to achieve asymptotic performance. Episodic Reinforcement Learning (ERL) algorithms, inspire…

Deep Reinforcement Learning Hippocampus reinforcement-learning Reinforcement Learning+1