研究人员正在开发新的框架来增强AI模型中的代理能力，特别是在视频生成和空间推理方面。ReTAC专注于视频空间推理的残差测试时计算，确保额外计算仅在需要时应用，并在失败时重新计算受影响的状态。类似地，GenRevisit通过允许代理重新访问之前的图像状态并进行改进来解决组合图像生成中的挑战，从而改进了对动作的信用分配。另一种方法，Any Time, Any Space (ATAS)，为长篇代理视频生成提供了一个以世界状态为中心的框架，利用场景和事件记忆来在镜头之间保持空间和时间一致性。这些进展旨在提高AI生成内容的连贯性和准确性。
AI
arXiv:2610.16315v1 Announce Type: new Abstract: Test-time agentic computation can improve multimodal large language models (MLLMs) through planning, tool use, iterative perception, and reflection, but indiscriminate computation may duplicate resolved work, introduce noisy evidenc…
arXiv:2610.14852v1 Announce Type: cross Abstract: Reinforcement learning (RL) is promising for spatial text-to-image generation, but existing work largely focuses on policy optimization, assuming accurate rewards and effective online rollouts. We observe in-domain gains with out-…
Long-form agentic video generation must turn a screenplay into shots that remain spatially and temporally consistent across nonconsecutive requests. Passing prompts or recent frames between shots does not provide a shared spatial frame for revisiting a scene or a time-indexed rec…
Understanding and tracking a dynamic world are fundamental to visual intelligence. Existing video benchmarks provide limited insight into whether models can maintain a coherent understanding of evolving world state. Building such a benchmark from real-world videos is challenging …
arXiv:2610.20571v1 Announce Type: new Abstract: Long-form agentic video generation must turn a screenplay into shots that remain spatially and temporally consistent across nonconsecutive requests. Passing prompts or recent frames between shots does not provide a shared spatial fr…
