利用智能代理AI构建3D游戏与程序化虚拟世界方向博士研究员

PhD Studentship: Building 3D Games and Procedural Worlds with Agentic AI

The University of East Anglia · 英国 · Norwich

原帖优先:申请材料、截止时间与资格以原帖和学校官方说明为准。

AI 中文速览

研究内容
本项目研究计算机图形学与生成式AI的交叉领域,旨在推进AI系统设计、构建和完善交互式3D游戏与虚拟世界的方法,将高层创意转化为完整、可玩的体验。具体方向包括开发能够规划复杂创意任务并使用游戏开发工具的智能代理AI、结合程序化内容生成与多模态生成模型创建多样化可编辑环境、研究工具使用与多代理协作、开发自动化游戏测试与反馈机制,以及探索人机协作方法。
申请条件
最低入学要求为计算机科学、计算机工程、应用数学或物理学专业二级甲等(2:1)荣誉学士学位。
待遇
提供为期3年的英国本土学费以及每年20,409英镑的生活补助(受2027/28年度商定的通胀上调影响)。
申请方式
原文未说明具体的申请方式、截止日期及提交网址,属于理学院资助奖学金的竞争选拔。

由 gemini-2.5-flash-lite 生成,博士岗判定置信度 100%。

岗位信息

截止
(Europe/London) 剩 93 天
学科
计算机科学
合同类型
雇佣合同
原文薪资
GBP 20,409 / 年(税前)
税后月薪(估)
¥12,800;房租后 ¥4,500
估算假设
单身、无子女、雇佣合同的粗略估算,以学校 offer 为准;扣除率 18%;汇率日期 2026-10-01
原帖发布
本站收录
内容更新
原帖导师候选(待核验)
Dr Cheng Wang
来源
jobs.ac.uk(英国博士项目及学术招聘) · 最近核对 2026-11-21
详情核验
判定依据(原文摘录)
  • english_ok
    The minimum entry requirement is 2:1 in Computer Science, Computer Engineering, Applied Maths or Physics.
  • bachelor_ok
    The minimum entry requirement is 2:1 in Computer Science, Computer Engineering, Applied Maths or Physics.
原文

Primary Supervisor: Dr Cheng Wang

We are seeking an outstanding PhD candidate to join our research group, working at the intersection of computer graphics and generative AI. This project aims to advance how AI systems design, build, and refine interactive 3D games and virtual worlds, transforming high-level creative ideas into coherent, playable experiences.

Research Focus

The PhD will investigate agentic AI systems that can plan complex creative tasks, use game development tools, and iteratively evaluate and improve their outputs. Moving beyond the generation of individual assets, the project will explore how AI can integrate 3D content, spatial layouts, game logic, and interactive behaviours into complete virtual environments. Specific objectives may include:

• Developing AI agents that translate natural-language descriptions, visual references, and design constraints into structured 3D worlds and playable game prototypes.

• Combining procedural content generation with multimodal generative models to create diverse, editable environments with consistent geometry, semantics, and visual style.

• Investigating tool use and multi-agent collaboration for coordinating asset creation, scene assembly, scripting, and simulation within game engines.

• Developing automated playtesting and feedback mechanisms to assess and improve navigability, gameplay functionality, and alignment with creative intent.

• Exploring human-AI collaboration methods that give designers meaningful control over world generation and iterative refinement.

The project combines fundamental research in planning, spatial reasoning, and generative modelling with practical innovation in game development and interactive world creation. A central challenge is ensuring that generated worlds are not only visually compelling, but also functional, coherent, and responsive to player interaction. The research will target leading venues in computer graphics, computer vision, and AI, including SIGGRAPH, CVPR, and NeurIPS.

Environment and Supervision

You will join a vibrant research lab, collaborating with researchers in computer vision, computer graphics, and AI. The supervisor will support the student in pursuing industrial internships and collaborations relevant to AI, graphics, and game development.

Entry Requirements

The minimum entry requirement is 2:1 in Computer Science, Computer Engineering, Applied Maths or Physics.

Start date: 1 st October 2027

Funding Details

This PhD project is in a competition for a Faculty of Science funded studentship. Funding is available to UK applicants and comprises ‘home’ tuition fees and an annual stipend for 3 years. The current UEA / institutional PhD stipend rate is £20,409 and will be subject to any agreed inflationary uplift for 2027/28.

信息有误?提交纠错