Saved in:
Bibliographic Details
Main Authors: Ma, Kexin, Li, Bojun, Tang, Yuhua, Sun, Liting, Jin, Ruochun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.06051
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915803414134784
author Ma, Kexin
Li, Bojun
Tang, Yuhua
Sun, Liting
Jin, Ruochun
author_facet Ma, Kexin
Li, Bojun
Tang, Yuhua
Sun, Liting
Jin, Ruochun
contents 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 experience as structures such as key-value, vector, or graph, which makes them struggle to represent and retrieve coherent events. To address this challenge, we propose a Character-and-Scene based memory architecture(CAST) inspired by dramatic theory. Specifically, CAST constructs 3D scenes (time/place/topic) and organizes them into character profiles that summarize the events of a character to represent episodic memory. Moreover, CAST complements this episodic memory with a graph-based semantic memory, which yields a robust dual memory design. Experiments demonstrate that CAST has averagely improved 8.11% F1 and 10.21% J(LLM-as-a-Judge) than baselines on various datasets, especially on open and time-sensitive conversational questions.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06051
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CAST: Character-and-Scene Episodic Memory for Agents
Ma, Kexin
Li, Bojun
Tang, Yuhua
Sun, Liting
Jin, Ruochun
Computation and Language
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 experience as structures such as key-value, vector, or graph, which makes them struggle to represent and retrieve coherent events. To address this challenge, we propose a Character-and-Scene based memory architecture(CAST) inspired by dramatic theory. Specifically, CAST constructs 3D scenes (time/place/topic) and organizes them into character profiles that summarize the events of a character to represent episodic memory. Moreover, CAST complements this episodic memory with a graph-based semantic memory, which yields a robust dual memory design. Experiments demonstrate that CAST has averagely improved 8.11% F1 and 10.21% J(LLM-as-a-Judge) than baselines on various datasets, especially on open and time-sensitive conversational questions.
title CAST: Character-and-Scene Episodic Memory for Agents
topic Computation and Language
url https://arxiv.org/abs/2602.06051