I am a PhD student at the University of Glasgow, working on trustworthy multi-agent AI systems, selective commitment, and Byzantine-resilient semantic collaboration.
My current research studies how multi-agent AI systems can decide when to commit, when to abstain, and when to safely abort under semantic poisoning, adversarial disagreement, and unreliable evidence.
- Trustworthy Multi-Agent AI
- LLM-Agent Collaboration
- Selective Commitment and Safe Abstention
- Byzantine-Resilient Semantic Systems
- Evidence-Aware Decision Protocols
- AI Safety and Trustworthy AI Infrastructure
I am developing protocol-level mechanisms for trustworthy multi-agent collaboration, with a focus on semantic commitment, evidence-aware compatibility, certificate-based finality, and safe-abort mechanisms.
- CRSE / FBA Encoder — Robust semantic encoder for Byzantine-resilient semantic agreement.
- LLM API Demos — Lightweight examples for structured LLM interaction and agent-related experimentation.
- Work Planner — Local-first academic productivity tool for planning and execution.
- ORCID: https://orcid.org/0009-0000-6659-2043
- LinkedIn: www.linkedin.com/in/haoran-xu-2454b0336
- Personal Website: https://hrxualbert.github.io