arXiv cs.AI· Yingzhao Jian, Zhongan Wang, Yuxuan Hou, Hehe Fan·· 1 天前AI 评分31
LIT：让视频导演智能体在交互与执导中协同进化
Learning to Interact and Direct: Co-Evolving Video Director Agents
AI 导读
研究提出 LIT 框架，由导演智能体、模拟用户和元工程师组成进化闭环，元智能体主动学习外部知识以发现并解决问题。在 Test 与 OOD Test 划分上，LIT 的制作与交互得分分别较初始流程提升 19.1% 和 32.0%。消融实验显示制作与交互能力的提升相互关联，协同进化机制进一步促进了执导技能与交互模式的探索。
正文 · 原文
Abstract:Video director agents orchestrate multistage production to realize users' creative visions. Emerging research on their self-evolution advances screenplay planning effectively. However, the mutual reinforcement between directing and user interaction remains largely overlooked. Improved interaction clarifies user intent and informs workflow refinement, while more reliable execution shifts collaboration from troubleshooting to creative decisions. To this end, we introduce LIT (Learning to Interact and DirecT), a framework comprises a director agent, a simulated user, and a meta engineer. Simulated user assigns creative tasks to probe the director's weaknesses, while the meta engineer uses the task traces to revise the director's interaction and production strategy. Although this approach can address discovered interaction and production issues, it still relies on passive attribution by the meta agent. This limits its ability to adapt to broader user interaction patterns and production techniques. To solve this problem, we equip LIT with a co-evolution paradigm. The meta agent proactively learns external knowledge, thereby improving its ability to discover problems and propose solutions. The meta agent, simulated user, and director together form an evolutionary closed loop, collaboratively enhances the system's directing and interaction capabilities. Across the Test and OOD Test splits, LIT improves production and Interaction scores by 19.1% and 32.0%, respectively, relative to the initial pipeline. Controlled ablations reveal the correlation between improvements in production and interaction, where the co-evolution mechanism further encourage directing skill and interaction mode exploration.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.41865 [cs.AI] |
| (or arXiv:2610.41865v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41865 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yingzhao Jian [view email]
[v1]
Fri, 30 Oct 2026 15:18:07 UTC (16,570 KB)
来源：arXiv cs.AI · arxiv.org