MemPrism: 長期的エージェントのためのタスク条件付き関係メモリビュー
MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents
長期タスクのエージェント向けに、経験を永続的に保存しつつ、現在のタスクに応じて動的に関係性を構築するメモリフレームワークを提案。固定表現による表現ミスマッチを解消し、長い軌跡での性能向上とメモリ消費削減を実証。
著者: Zhisheng Chen, Bingfan Zeng, Bangde Cao, Zhengwei Xie, Yuxuan Li, Jinhan Li, Zheng Lu, Xiangchen Guan, Zikai Xiao, Rui Qian, Jingwei Song
分類: cs.AI
原文アブストラクト
Long-horizon agents rely on memory to reuse experiences, yet existing memory systems often assume that evidence can be directly consumed through a fixed representation. This leads to representation mismatch, where relevant information is available but not organized for the current decision. 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 render 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.