Cognitive Intelligence in Self-Evolving Multi-Agent Systems PhD

We invite applications for a self-funded PhD to advance cognitive intelligence in self-evolving multi-agent systems, moving beyond conventional embodied AI towards human-inspired cognitive reasoning, adaptive collective intelligence and seamless human–autonomy collaboration. This research will investigate how autonomous agents develop and evolve cognitive capabilities, such as intention understanding, trust reasoning, and social intelligence, to enable effective cooperation with humans and other agents. Candidates will explore foundation models, multi-agent reinforcement learning or related cognitive architectures, with applications in challenging, time-critical environments such as search and rescue.

Recent breakthroughs in embodied AI, foundation models, and autonomous robotics have enabled intelligent agents to perceive, reason, and act in increasingly complex environments. However, existing systems remain predominantly task-driven, with limited capabilities to understand human cognition, reason about other agents' intentions, or continuously evolve their cognitive behaviours through interaction.

This PhD aims to push beyond conventional embodied intelligence towards human-inspired, self-evolving cognitive intelligence in multi-agent systems. The research will investigate how autonomous agents can develop cognitive mechanisms, including situational awareness understanding, trust reasoning, and social intelligence, and how these capabilities can emerge, adapt and co-evolve through human–agent and agent–agent interactions.

Candidates will have opportunities to explore cutting-edge AI methodologies, including multimodal foundation models, multi-agent reinforcement learning, and continual collective intelligence. Research directions are flexible, encouraging applicants to develop innovative approaches.

Students undertaking this project will be embedded within Cranfield's world-leading research ecosystem, working at the Human-Machine-X Collaboration (HUMAX) Lab. They will have the opportunity to collaborate with major industrial partners across aerospace, defence, and transport sectors, benefiting from Cranfield's strong industry networks and applied research culture. Throughout the programme, the student will be fully supported to produce high-quality scientific outputs and develop a strong international profile.

Entry Requirements: Applicants should at least have a first- or second-class UK bachelor's degree or equivalent in a related discipline. This project would suit candidates with a sound background in engineering, computer science, or related disciplines.

Funding: This is a self-funded PhD. Applicants are responsible for tuition fees and living costs.

Research students at Cranfield benefit from being part of a dynamic, focused and professional study environment and all become valued members of the Cranfield Doctoral Network. This Network brings together both research students and staff, providing a platform for researchers to share ideas, identify opportunities for collaboration and create smaller communities of practice.

An important part of the research journey is developing key skills. As a research student at Cranfield, you will be expected to attend the Doctoral Researchers' Core Development (DRCD) programme which comprises four 1-week units covering the key stages of your research journey. Workshops are held face to face, providing the opportunity to network and collaborate with peers.

First Supervisor: Dr Yang Xing, Senior Lecturer in Applied Artificial Intelligence for Engineering.