Papers
arxiv:2608.07107

MemWM: Memory-Augmented Text-Based World Model

Published on Aug 21
Authors:
,
,
,
,
,
,
,
,
,
,
,

Abstract

MemWM improves text-based world models via a curated memory bank and policy-side corrective guidance, boosting factual state fidelity and planning success across interactive benchmarks.

World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent next-state predictions can still omit task-critical facts, corrupt product attributes, or apply incorrect transition rules. To address such systematic prediction errors, we introduce MemWM, a memory-augmented text-based world model. MemWM uses world memory, a curated memory bank of transition rules, state caches, and hard-to-predict facts, to condition next-state imagination. We evaluate factual state preservation with Structured State Fidelity (SSF), which scores predicted states through benchmark-specific facts and fields. Compared with SFT, memory-augmented training improves SSF by up to 206.3%. In the full planning setting, we keep the policy model frozen and provide policy-side world skill: retrieved task-level skills and step-wise corrective guidance for action selection. Across ALFWorld, WebShop, and ScienceWorld, memory-augmented agents improve downstream success over an SFT-trained world-model agent, with up to a 65.4% relative gain. Sensitivity analyses further show that retrieved memory improves task success and efficiency under different memory and action-budget settings.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2608.07107
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2608.07107 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2608.07107 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2608.07107 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.