PhD: Self-Evolving Agents: Continual, Trustworthy, and Resource-Efficient Agentic AI

PhD: Self-Evolving Agents: Continual, Trustworthy, and Resource-Efficient Agentic AI

Job No.: 698514

Location: Clayton campus

Employment Type: Full-time

Duration: The scholarship may be held for up to 4 years (fulltime) for Research Doctorate (PhD) studies.

Remuneration: The successful applicant will receive:

The Opportunity

As part of the CSIRO Industry PhD scholarship program, this is an unprecedented opportunity for an outstanding data science and AI PhD candidate interested in agentic AI, supervised by Dr Teresa Wang and Dr Tongtong Wu at Monash University, jointly with Dr He Zhao and Dr, Dan Steinberg from CSIRO, Dr Yue Yang and David Lemphers from Maincode.

Advances in large language models and agentic AI have enabled autonomous systems that can reason, plan, retrieve information, and use external tools. However, most existing agent frameworks remain largely static: their knowledge, internal organisation, and coordination strategies are typically predefined. This makes them brittle in dynamic environments where information, tasks, and requirements continuously evolve.

This project investigates self-evolving agentic AI systems, i.e., adaptive AI agents that can continually acquire new knowledge, reorganise their collaboration structures, and improve their performance over time.

The student will be able work on cutting-edge AI/ML/LLM topics closely with leading experts in Monash University, CSIRO, and Maincode and access to the computational resources in these organisations. The student will also gain valuable industrial experience from Maincode who could provide a solid testbed for the work, which would help transition the research into real-world applications.

To be considered for this opportunity you should fulfil the eligibility requirements listed below.

The ideal PhD candidate will have:

Monash University strongly advocates diversity, equality, fairness and openness. We fully support the gender equity principles of the Athena SWAN Charter.

The Project

This project investigates self-evolving agentic AI systems, i.e., adaptive AI agents that can continually acquire new knowledge, reorganise their collaboration structures, and improve their performance over time. The research will explore methods for continual knowledge integration, adaptive multi-agent orchestration, and knowledge-grounded reasoning using structured resources such as ontologies and knowledge graphs. It will also study approaches for building efficient and trustworthy agent systems that can scale to complex tasks.

The project aims to develop a unified framework for building agentic AI systems that can operate as long-term collaborators, continuously learning and adapting as their environments and objectives change. By combining ideas from continual learning, multi-agent systems, and knowledge-grounded reasoning, this research seeks to advance the foundations of adaptive AI systems capable of sustained, reliable performance in evolving knowledge environments.

This position has a two-stage selection process:

Stage 1: Please submit to fit-graduate.research@monash.edu.

With the EOI please include the documents - CV, academic transcripts and grading scale, a cover letter and a draft research proposal of up to 2 pages, responding to one or more of the above research objectives.

The draft research proposal should outline your interest in being a PhD candidate and summarise the theoretical and methodological approaches you are interested in pursuing, such as continual learning, multi-agent systems, and knowledge-grounded reasoning.

Stage 2: Candidates who pass this stage of the selection process will be invited to discuss their ideas with the supervisory team before developing and submitting a full application.

Enquiries:fit-graduate.research@monash.edu or supervisor email address

Further information:

Applications Close: Friday 13th November 2026, 11:55 pm AEST