MemWM: Memory-Augmented Text-Based World Model

• URL: http://arxiv.org/abs/2608.07107v1
• Date: Fri, 07 Aug 2026 11:03:32 GMT
• Title: MemWM: Memory-Augmented Text-Based World Model
• Abstract summary: We introduce MemWM, a memory-augmented text-based world model.<n>MemWM uses world memory, a curated memory bank of transition rules, state caches, and hard-to-predict facts.<n>We evaluate factual state preservation with Structured State Fidelity (SSF), which scores predicted states through benchmark-specific facts and fields.<n>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.
• Score: 49.654556986087535
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Towards Evolving Context Parameterization for Large Language Models [13.314849988154707]
  PLUME is a training-free method that constructs a global update representation and activates memory evidence to form a local parameter view.<n>We show PLUME's effectiveness in sequential evolution settings, yielding relative improvements of 29.9% in average ROUGE-L Recall and 54.9% in LLM-as-a-Judge.
  arXiv  Detail & Related papers  (2026-09-12T21:55:33Z)
• Mimir: A Neuro-Symbolic Memory System with Dynamic Grounding for Embodied Agents in Interactive Environments [15.524473346555395]
  Long-horizon embodied task requires agents to act under partial observability while preserving both scene belief and execution progress.<n>We introduce Mimir, a neuro-symbolic memory that separates world memory from task memory and dynamically grounds them before each action.<n>Across tested backbones, Mimir consistently improves on different EB-ALFRED and EB-Habitat tasks, with maximum gains of 42.5% and average gains of 23.0%, respectively.
  arXiv  Detail & Related papers  (2026-08-05T14:57:24Z)
• Self-Evolving World Models for LLM Agent Planning [72.99782619992361]
  We introduce WorldEvolver, a self-evolving world model framework that revises its deployment-time context while keeping the downstream agent and all model parameters frozen.<n>WorldEvolver achieves the highest prediction accuracy across three backbones and leads other world model baselines on downstream agent success rate.
  arXiv  Detail & Related papers  (2026-06-29T17:58:43Z)
• STAMP: Training Explicit Memory for Mobile GUI Agents in Controllable and Scalable Virtual Environments [63.39393178045112]
  Mobile agents excel at immediate reactive control but frequently fail in realistic, longhorizon tasks that require memory.<n>We present STAMP, a framework that trains explicit memory in mobile agents through controllable virtual environments.<n>The resulting StampGUI agent sets a new high watermark on our Memory-World benchmark, demonstrating exceptional memory accuracy and task resilience.
  arXiv  Detail & Related papers  (2026-05-28T04:00:13Z)
• Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory [53.8372503928207]
  Large language model (LLM) agents require long-term user memory for consistent personalization.<n>Existing memory systems mainly rely on static, hand-crafted update rules.<n>We introduce MemCoE, a cognition-inspired two-stage optimization framework that learns how memory should be organized and what information to update.
  arXiv  Detail & Related papers  (2026-05-01T14:45:20Z)
• Beyond State Consistency: Behavior Consistency in Text-Based World Models [58.216587360435305]
  We introduce a new behavior-aligned training paradigm aimed at improving the functional consistency between the world model and the real environment.<n> Experiments on WebShop and TextWorld show that BehR-based training improves long-term alignment in several settings.
  arXiv  Detail & Related papers  (2026-04-15T12:56:45Z)
• MAGNET: Towards Adaptive GUI Agents with Memory-Driven Knowledge Evolution [44.92687597179025]
  Mobile agents powered by large foundation models enable autonomous task execution, but frequent updates cause agents trained on historical data to fail.<n>We introduce MAGNET, a memory-driven adaptive agent framework with dual-level memory.<n>Online benchmark AndroidWorld evaluations show substantial improvements over baselines, while offline benchmarks confirm consistent gains under distribution shifts.
  arXiv  Detail & Related papers  (2026-01-27T04:58:48Z)
• Memp: Exploring Agent Procedural Memory [72.41472703974935]
  Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters.<n>We propose Memp that distills past agent trajectories into both fine-grained, step-by-step instructions and higher-level, script-like abstractions.<n>We show that as the memory repository is refined, agents achieve steadily higher success rates and greater efficiency on analogous tasks.
  arXiv  Detail & Related papers  (2025-08-08T16:20:56Z)
• Think Before You Act: Decision Transformers with Working Memory [44.18926449252084]
  Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training. We propose a working memory module to store, blend, and retrieve information for different downstream tasks.
  arXiv  Detail & Related papers  (2023-05-24T01:20:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.