ByteDance Seed
首页模型博客&论文Seed Edge加入我们
体验豆包AI 体验中心
首页模型博客&论文Seed Edge加入我们
体验豆包AI 体验中心

2026-05-29

Task-Focused Memorization for Multimodal Agents

Download PDF
上一篇下一篇

摘要

Long-term memory is essential for multimodal agents to build coherent experience, accumulate world knowledge, and achieve continual learning. However, constructing effective memory goes beyond memory module design and basic requirements such as accuracy and fidelity; the key challenge lies in determining what to memorize. Multimodal agents, such as embodied agents, continuously perceive, reason, and act in real or virtual environments, receiving an unbounded stream of multimodal observations. From this combinatorial explosion of information, an agent must selectively retain content that is relevant to its role in the environment and valuable for future tasks. To bridge this gap, we frame memory generation as a learnable memorization policy and introduce TaskMem (Task-focused Memorization Policy Learning), a reinforcement-learning-based framework that enables the policy to dynamically adjust its focus to the demands of real tasks encountered in the environment. TaskMem adopts a two-phase training paradigm: Phase One learns how to memorize by optimizing memory quality under fundamental fidelity requirements; Phase Two occurs after deployment, where the agent learns what to memorize by tuning an adapter on its base MLLM, using recent environment tasks to define a reward model that guides the memorization policy toward task-relevant content. To evaluate our approach, we reformulate VideoMME, EgoLife, and EgoTempo into streaming benchmarks that simulate a realistic setting in which an agent processes streaming observations and handles tasks arriving online. To isolate memory assessment, the questions must be answered using only the agent's memory, without access to raw video. Built on Qwen3-VL-30B-A3B, TaskMem improves VQA accuracy by 6.3%, 7.0%, and 5.3% on these benchmarks, respectively.

作者

Tao Zou, Yichen He, Tian Qiu, Yuan Lin, Hang Li

期刊/会议

arXiv

追求智能上限,创造社会价值
字节跳动 Seed 招聘二维码
欢迎加入字节跳动 Seed
Copyright© 2026 Bytedance Seed
网站声明联系我们 : seed.feedback@bytedance.com
追求智能上限,创造社会价值
字节跳动 Seed 招聘二维码
欢迎加入字节跳动 Seed
联系我们 : seed.feedback@bytedance.com
Copyright© 2026 Bytedance Seed网站声明联系我们 : seed.feedback@bytedance.com