arXiv cs.AI· Bingfan Zeng, Zhisheng Chen, Zhengwei Xie, Bangde Cao, Yuxuan Li, Jinhan Li, Zheng Lu, Xiangchen Guan, Zikai Xiao, Rui Qian, Jingwei Song·· 3 小时前AI 评分41
MemPrism：面向长程智能体的任务条件关系记忆框架
MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents
AI 导读
研究者提出 MemPrism，一个任务条件关系记忆框架，将持久经验存储与决策时工作记忆分离，解决长程智能体的表征失配问题。它以事件流记录交互，由轻量级视图策略动态选择关系结构、证据范围与粒度，生成临时光学工作记忆视图。在长程具身与 web-agent 基准上持续提升任务表现并降低记忆 token 消耗，所学视图策略可跨 VLM 迁移而无需额外适配。
正文 · 原文
Authors:Bingfan Zeng, Zhisheng Chen, Zhengwei Xie, Bangde Cao, Yuxuan Li, Jinhan Li, Zheng Lu, Xiangchen Guan, Zikai Xiao, Rui Qian, Jingwei Song
Abstract:Long-horizon agents performing multi-step Web tasks must reuse earlier page observations and interactions to support subsequent actions. However, preserving relevant history does not ensure that it exposes the relations needed for the current decision. We call this gap representation mismatch. To this end, we propose MemPrism, a task-conditioned relational memory framework that separates persistent experience storage from decision-time working memory. MemPrism records interactions as the event stream and dynamically constructs relational views according to the current task context. A lightweight view policy selects the relation structure, evidence range, outcome condition, and granularity, while a deterministic composer and renderer transform historical facts into a temporary optical working-memory view for a frozen task policy. Experiments on long-horizon embodied and web-agent benchmarks show that MemPrism consistently improves the task performance, especially as trajectories become longer, while reducing memory token consumption. Furthermore, the learned view policy transfers across different VLMs without additional adaptation, demonstrating the effectiveness of task-conditioned relational views as a general memory interface for agents.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2608.06745 [cs.AI] |
| (or arXiv:2608.06745v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2608.06745 arXiv-issued DOI via DataCite |
Submission history
From: Zhisheng Chen [view email]
[v1]
Fri, 7 Aug 2026 03:13:43 UTC (6,627 KB)
[v2]
Tue, 27 Oct 2026 10:39:17 UTC (4,986 KB)
来源：arXiv cs.AI · arxiv.org