WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory

• URL: http://arxiv.org/abs/2607.18840v1
• Date: Tue, 21 Jul 2026 08:25:37 GMT
• Title: WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory
• Abstract summary: We introduce WorldScape Policy 2.0, a controllable WAM with reasoning-augmented long short-term memory.<n>The retrieved history augments perception and autoregressively generated planning tokens, yielding an implicit subgoal condition for autonomous planning.<n>Experiments in both simulation and real-world platforms demonstrate superior capabilities in long-horizon autonomous planning, fine-grained instruction following, and in-context adaptation.
• Score: 50.19449886428936
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World Action Models (WAMs) offer a promising paradigm for robotic manipulation by jointly modeling visual state transitions and robot actions. However, existing WAMs are constrained by limited temporal context, coarse episode-level language supervision, and predominantly text-only conditioning, which hinder task-progress tracking and fine-grained language-video-action grounding while limiting visual-context reasoning and cross-embodiment transfer. In this paper, we introduce WorldScape Policy 2.0, a controllable WAM with reasoning-augmented long short-term memory. Its causal short-term visual memory supplies recent observations as DiT prefill to preserve local interaction dynamics, while its long short-term event memory organizes historical VLM outputs into global-history, local-active, and event-boundary representations for progress-aware retrieval. The retrieved history augments perception and autoregressively generated planning tokens, yielding an implicit subgoal condition for autonomous planning; semantic forcing further transfers event-level instruction semantics into this latent planning pathway. To establish fine-grained multimodal controllability, we construct ManipEvent-5M, an event-grounded embodied pretraining dataset containing nearly 5 million event segments with aligned action trajectories, episode-level task instructions, segment-level subtask captions, goal images, and video demonstrations. These designs provide a unified interface for autonomous planning from high-level instructions and controllable execution from fine-grained text, goal-image, or video-context prompts. Experiments in both simulation and real-world platforms demonstrate superior capabilities in long-horizon autonomous planning, fine-grained instruction following and in-context adaptation.

Related papers

• Memory as Plans: World-Action Modeling with Memory-Grounded Planning [33.29460541345171]
  MaP-WAM is a Memory-as-Plans framework that decomposes memory-dependent world-action modeling into memory-grounded planning and plan-conditioned execution.<n>MaP-WAM achieves state-of-the-art performance on RMBench with an 83.3% success rate and attains 78.0% success on real-robot tasks.
  arXiv  Detail & Related papers  (2026-09-10T13:52:51Z)
• EV-WM: Event-Verified World Models for Long-Horizon Robotic Manipulation [0.815557531820863]
  Long-horizon manipulation requires progress signals that are relational, predicate-level, and physically grounded.<n>We introduce textbfEV-WM, a predicate-grounded verification framework for world-model planning.
  arXiv  Detail & Related papers  (2026-06-11T08:35:37Z)
• Task Robustness via Re-Labelling Vision-Action Robot Data [15.985610886484226]
  This paper introduces Task Robustness via Re-Labelling Vision-Action Robot Data (TREAD), a scalable framework to augment existing robotics datasets.<n>Our approach leverages a pretrained VLM through three stages: generating semantic sub-tasks from original instruction labels and initial scenes, segmenting demonstration videos conditioned on these sub-tasks, and producing diverse instructions that incorporate object properties.<n>Our results show that TREAD enhances both planning generalization through trajectory decomposition and language-conditioned policy generalization through increased linguistic diversity.
  arXiv  Detail & Related papers  (2026-06-09T14:28:22Z)
• Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models [101.44987067974999]
  Coarse-to-Control is a plan-execute VLA that introduces planning in the action-token space.<n>We show that action-token planning consistently improves over direct action generation.
  arXiv  Detail & Related papers  (2026-06-05T10:01:37Z)
• AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding [55.535374902204296]
  AffordanceVLA is a unified framework that introduces structured affordance forecasting as a task-oriented intermediate representation.<n>We show that AffordanceVLA achieves strong performance across diverse manipulation scenarios.
  arXiv  Detail & Related papers  (2026-06-04T13:28:51Z)
• MoMaStage: Skill-State Graph Guided Planning and Closed-Loop Execution for Long-Horizon Indoor Mobile Manipulation [27.117666227269044]
  Indoor mobile manipulation (MoMA) enables robots to translate natural language instructions into physical actions.<n>MoMaStage is a vision-language framework for long-horizon MoMA that eliminates the need for explicit scene mapping.<n> experiments in physics-rich simulations and real-world environments demonstrate that MoMaStage outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-09T13:43:38Z)
• Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation [37.76888706583038]
  Long-horizon robotic manipulation is increasingly important for real-world deployment.<n>Existing end-to-end and hierarchical Vision-Language-Action policies often rely on text-only cues.<n>We introduce Visual Sketch, an implausible visual intermediate that renders points, boxes, arrows, and typed relations in the robot's current views.<n>We present Action-Sketcher, a VLA framework that operates in a cyclic See-Think-Sketch-Act workflow.
  arXiv  Detail & Related papers  (2026-01-04T17:53:42Z)
• Gondola: Grounded Vision Language Planning for Generalizable Robotic Manipulation [62.711546725154314]
  We introduce Gondola, a grounded vision-language planning model based on large language models (LLMs) for generalizable robotic manipulation.<n>G Gondola takes multi-view images and history plans to produce the next action plan with interleaved texts and segmentation masks of target objects and locations.<n>G Gondola outperforms the state-of-the-art LLM-based method across all four levels of the GemBench dataset.
  arXiv  Detail & Related papers  (2025-06-12T20:04:31Z)
• Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies.<n>Our findings are synthesized in Flex (Fly lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors.<n>We demonstrate the effectiveness of this approach on a quadrotor fly-to-target task, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)
• LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments [70.91258869156353]
  We introduce LangSuitE, a versatile and simulation-free testbed featuring 6 representative embodied tasks in textual embodied worlds. Compared with previous LLM-based testbeds, LangSuitE offers adaptability to diverse environments without multiple simulation engines. We devise a novel chain-of-thought (CoT) schema, EmMem, which summarizes embodied states w.r.t. history information.
  arXiv  Detail & Related papers  (2024-06-24T03:36:29Z)

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.