SPIRAL: A Closed-Loop Framework for Self-Improving Action World Models via Reflective Planning Agents

• URL: http://arxiv.org/abs/2603.08403v2
• Date: Wed, 11 Mar 2026 02:50:34 GMT
• Title: SPIRAL: A Closed-Loop Framework for Self-Improving Action World Models via Reflective Planning Agents
• Abstract summary: We introduce SPIRAL, a self-improving planning and iterative reflective action world modeling framework.<n> SPIRAL formulates ActWM as a closed-loop think-act-reflect process, where generation proceeds step by step under explicit planning and feedback.<n> Experiments across multiple TI2V backbones demonstrate consistent gains on ActWM-Bench and mainstream video generation benchmarks.
• Score: 135.00390535239129
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce SPIRAL, a self-improving planning and iterative reflective action world modeling closed-loop framework that enables controllable long-horizon video generation conditioned on high-level semantic actions. Existing one-shot video generation models operate in open-loop, often resulting in incomplete action execution, weak semantic grounding, and temporal drift. SPIRAL formulates ActWM as a closed-loop think-act-reflect process, where generation proceeds step by step under explicit planning and feedback. A PlanAgent decomposes abstract actions into object-centric sub-actions, while a CriticAgent evaluates intermediate results and guides iterative refinement with long-horizon memory. This closed-loop design naturally supports RL evolving optimization, improving semantic alignment and temporal consistency over extended horizons. We further introduce the ActWM-Dataset and ActWM-Bench for training and evaluation. Experiments across multiple TI2V backbones demonstrate consistent gains on ActWM-Bench and mainstream video generation benchmarks, validating SPIRAL's effectiveness.

Related papers

• WALL-SS: Scaling Long-horizon World Models via Next-Scale Autoregression [24.010807495676605]
  Generative world models provide robots with predictive models of how the world evolves under interaction.<n>We introduce WALL-SS, a world model that generates visual futures through Scale-wise autoregressive Scaling.<n>We show that WALL-SS improves action following and trajectory accuracy, supports coherent minute-long streaming rollout under bounded memory, and consistently benefits from on-policy alignment.
  arXiv  Detail & Related papers  (2026-08-26T17:57:12Z)
• Reflex: Enabling Fast and Predictive Vision-Language-Action Models for Reaction-Critical Manipulation [15.635041548277492]
  Vision-Language-Action (VLA) models have recently achieved promising performance in robotic manipulation.<n>We present ReflexBench, a benchmark for reaction-critical manipulation.<n>Building upon ReflexBench, we propose ReflexVLA, an efficient VLA model for reaction-critical manipulation.
  arXiv  Detail & Related papers  (2026-08-14T15:19:04Z)
• Native Video-Action Pretraining for Generalizable Robot Control [77.59831077077176]
  LingBot-VA 2.0 is a video-action foundation model built from the ground up for embodiment.<n>To meet the demands of high-frequency inference, our model employs a sparse MoE backbone.<n>Real-world deployment validates LingBot-VA 2.0 as a robust foundation model.
  arXiv  Detail & Related papers  (2026-07-09T16:15:43Z)
• Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization [56.150184676745205]
  Video anomaly understanding (VAU) relies on sparse, context-dependent cues.<n>We propose $Anomtext-$, a closed-loop framework that reconceptualizes video understanding as an active sequential decision-making process.<n>Inspired by human video-reviewing behavior, this framework unifies internal cognitive reasoning and strategic evidence acquisition into an interleaved policy.
  arXiv  Detail & Related papers  (2026-07-01T08:41:49Z)
• AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing [45.6226084109777]
  We propose AHA-WAM, an Asynchronous Horizon-Adaptive World-Action Model built on a dual Diffusion Transformer (DiT) architecture.<n>We show that AHA-WAM achieves state-of-the-art performance without any robot-data pretraining, attaining 92.80% average success on RoboTwin and 78.3% success across 4 real-world tasks.
  arXiv  Detail & Related papers  (2026-06-08T17:55:18Z)
• RotVLA: Rotational Latent Action for Vision-Language-Action Model [54.22746299071677]
  We introduce RotVLA, a VLA framework built on a continuous rotational latent action representation.<n>Latent actions are modeled as elements of SO(n), providing continuity, compositionality, and structured geometry aligned with real-world action dynamics.<n>RotVLA consists of a VLM backbone and a flow-matching action head, pretrained on large-scale cross-embodiment robotic datasets and human videos.
  arXiv  Detail & Related papers  (2026-05-13T11:58:02Z)
• ResWM: Residual-Action World Model for Visual RL [0.06999740786886534]
  Learning predictive world models from raw visual observations is a central challenge in reinforcement learning (RL)<n>We introduce the Residual-Action World Model (ResWM), a new framework that reformulates the control variable from absolute actions to residual actions.<n>ResWM produces more stable and energy-efficient action trajectories, a property critical for robotic systems deployed in real-world environments.
  arXiv  Detail & Related papers  (2026-03-11T11:27:08Z)
• Chain of World: World Model Thinking in Latent Motion [24.24061036481793]
  Vision-Language-Action (VLA) models often overlook the predictive and temporal-causal structure underlying visual dynamics.<n>We introduce CoWVLA, a new "Chain of World" paradigm that unifies world-model temporal reasoning with a disentangled latent motion representation.<n>CoWVLA outperforms existing world-model and latent-action approaches and achieves moderate computational efficiency.
  arXiv  Detail & Related papers  (2026-03-03T17:52:06Z)
• Generative Actor Critic [74.04971271003869]
  Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T06:31:11Z)
• STORM: Search-Guided Generative World Models for Robotic Manipulation [10.365032830677162]
  STORM is a framework for selectively-temporal reasoning in robotic manipulation.<n>It unifies diffusion-based action generation, conditional video prediction, and search-based planning.<n>Storm grounds planning in visuals, enabling interpretable and foresight-driven decision-making.
  arXiv  Detail & Related papers  (2025-12-20T19:40:25Z)
• SAMPO:Scale-wise Autoregression with Motion PrOmpt for generative world models [42.814012901180774]
  textbfSAMPO is a hybrid framework that combines visual autoregressive modeling for intra-frame generation with causal modeling for next-frame generation.<n>We show that SAMPO achieves competitive performance in action-conditioned video prediction and model-based control.<n>We also evaluate SAMPO's zero-shot generalization and scaling behavior, demonstrating its ability to generalize to unseen tasks.
  arXiv  Detail & Related papers  (2025-09-19T02:41:37Z)
• ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer [58.49950218437718]
  We present ReCoM, an efficient framework for generating high-fidelity and generalizable human body motions synchronized with speech.<n>The core innovation lies in the Recurrent Embedded Transformer (RET), which integrates Dynamic Embedding Regularization (DER) into a Vision Transformer (ViT) core architecture.<n>To enhance model robustness, we incorporate the proposed DER strategy, which equips the model with dual capabilities of noise resistance and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-03-27T16:39:40Z)
• Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model [63.336123527432136]
  We introduce Bench2Drive-R, a generative framework that enables reactive closed-loop evaluation.<n>Unlike existing video generative models for autonomous driving, the proposed designs are tailored for interactive simulation.<n>We compare the generation quality of Bench2Drive-R with existing generative models and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-11T06:35:18Z)
• Diffusion Transformer Policy [48.50988753948537]
  We propose a large multi-modal diffusion transformer, dubbed as Diffusion Transformer Policy, to model continuous end-effector actions.<n>By leveraging the scaling capability of transformers, the proposed approach can effectively model continuous end-effector actions across large diverse robot datasets.
  arXiv  Detail & Related papers  (2024-10-21T12:43:54Z)
• JNMR: Joint Non-linear Motion Regression for Video Frame Interpolation [47.123769305867775]
  Video frame (VFI) aims to generate frames by warping learnable motions from the bidirectional historical references. We reformulate VFI as a Joint Non-linear Motion Regression (JNMR) strategy to model the complicated motions of inter-frame. We show that the effectiveness and significant improvement of joint motion regression compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-06-09T02:47:29Z)

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.