# SCOPE: Score-Isolated Agentic Optimization for Video World Models

arXiv: https://arxiv.org/abs/2608.15043 · HTML: https://mlsanity.com/paper/2608.15043/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 15 Aug 2026.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 23 of 23)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps](https://mlsanity.com/paper/2501.09732/) (2025)
- [SkillOpt: Executive Strategy for Self-Evolving Agent Skills](https://mlsanity.com/paper/2605.23904/) (2026)
- [Infinite Worlds with Versatile Interactions](https://mlsanity.com/paper/2607.07534/) (2026)
- [Inference-time Physics Alignment of Video Generative Models with Latent World Models](https://mlsanity.com/paper/2601.10553/) (2026)
- [Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents](https://mlsanity.com/paper/2605.30621/) (2026)
- [GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation](https://mlsanity.com/paper/2605.21605/) (2026)
- [SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale](https://mlsanity.com/paper/2606.03056/) (2026)
- [Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation](https://mlsanity.com/paper/2606.26907/) (2026)
- [PhyGround: Benchmarking Physical Reasoning in Generative World Models](https://mlsanity.com/paper/2605.10806/) (2026)
- [NEWTON: Agentic Planning for Physically Grounded Video Generation](https://mlsanity.com/paper/2605.18396/) (2026)
- [Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries](https://mlsanity.com/paper/2605.19576/) (2026)
- [PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation](https://mlsanity.com/paper/2606.28128/) (2026)
- [VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment](https://mlsanity.com/paper/2603.16271/) (2026)
- [SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agents](https://mlsanity.com/paper/2606.13317/) (2026)
- [WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors](https://mlsanity.com/paper/2605.10434/) (2026)
- [COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows](https://mlsanity.com/paper/2607.01709/) (2026)
- [Tiny Inference-Time Scaling with Latent Verifiers](https://mlsanity.com/paper/2603.22492/) (2026)
- [LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation](https://mlsanity.com/paper/2605.23878/) (2026)
- [Geo-Align: Video Generation Alignment via Metric Geometry Reward](https://mlsanity.com/paper/2605.23903/) (2026)
- [Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement](https://mlsanity.com/paper/2605.19317/) (2026)

## Abstract (arXiv)

Video world models are increasingly used as simulators for planning and embodied decision making, yet improving them at inference time introduces a subtle evaluation problem: prompts, samplers, verifiers, and selectors may evolve together, making it difficult to attribute gains or prevent held-out feedback from shaping the final policy. We introduce scope (scopefullname), a framework for auditable inference-time adaptation of frozen video world models. scope represents external controls as a typed state, updates this state only through bounded changes supported by development evidence, and freezes the resulting policy before held-out evaluation. On Physics-IQ benchmark, scope improves over the exact frozen base by +14.24 (95% CI [+8.10,+21.23]). Controlled ablations further identify gains from scene specification, sampling, and learned selection, while the margin over the strongest matched agentic baseline remains unresolved. Cross-backbone and prospective evaluations reveal a complementary result: useful inference-time updates exist, but their benefits do not transfer uniformly across models and settings. Together, these findings suggest that reliable inference-time adaptation requires not only better proposals, but also a principled mechanism for deciding which updates should become part of the deployed system. Code is available at https://github.com/YuhuaJiang2002/SCOPE.