Hi there ✦ Welcome to my homepage!

I research Autonomous Agentic AI and Recursive Self-Improving LLMs in the Department of Engineering, University of Cambridge, focusing on multi-agent systems, reinforcement learning and heuristic methods. I completed my MPhil research at SCAIL and am now pursuing my PhD, supervised by Prof. Alexandra Brintrup.

In October 2026, I launched Research Autopilot to help people navigate the full research process with their own human–AI team—from developing ideas and running experiments to writing, publishing and sharing their work.

News

Experience

University of Cambridge
2022 – 2026
MPhil & PhD, Department of Engineering

University of Birmingham
2020 – 2022
B.Eng., First-Class Honours · Research Assistant, Robotics Lab

Wuhan University of Technology
2018 – 2020
B.Sc. · GPA: 3.8/4.0 · WUTE Member

Shenzhen Middle School
2015 – 2018

Publications

EmoDistill
Yunbo Long, Haolang Zhao, Lukas Beckenbauer, Liming Xu, Alexandra Brintrup
Offline emotion-skill distillation for adversarial negotiation agents.

EMNLP 2026 · LLM Agents Track[arXiv]

VeriTrace
Haolang Zhao^*, Yunbo Long^*, Lukas Beckenbauer, Alexandra Brintrup
* Equal contribution.
Evolving cognitive graphs for reliable deep-research agents.

EMNLP 2026 · LLM Agents Track[arXiv]

EmoMAS
Yunbo Long, Yuhan Liu, Liming Xu
Bayesian orchestration for emotion-aware edge negotiation agents.

ACL 2026 · LLM Agents Track[arXiv]

EmoDebt
Yunbo Long, Yuhan Liu, Liming Xu, Alexandra Brintrup
Emotion-aware strategic reasoning for agent-to-agent debt recovery.

AAMAS 2026 · Main Track[arXiv]

GFC
Yunbo Long^*, Jiaquan Zhang^*, Xi Chen, Alexandra Brintrup
* Equal contribution.
One-shot private federated clustering with gravitational potential fields.

AAAI 2026 · Main Track[arXiv]

TabGRAA
Yunbo Long^*, Tejumade Afonja^*, Guangya Hao, Alexandra Brintrup, Mario Fritz
* Equal contribution.
Iterative reward-guided post-training for tabular language models.

arXiv 2026[arXiv]

Helicase
Yunbo Long, Haolang Zhao, Ge Zheng, Alexandra Brintrup
Uncertainty-guided supply-chain knowledge graph construction with autonomous agents.

arXiv 2026[arXiv]

AI-Supervisor
Yunbo Long
Autonomous research supervision through a persistent research world model.

arXiv 2026[arXiv]

TabKG
Yunbo Long, Ge Zheng, Liming Xu, Alexandra Brintrup
Logically consistent synthetic tables through LLM-driven knowledge graphs.

arXiv 2026[arXiv]

DecentMem
Guangya Hao, Yunbo Long, Zhuokai Zhao
Decentralized memory for self-evolving multi-agent systems.

arXiv 2026[arXiv]

ViSA-R2
Pengze Li, Jiaquan Zhang, Yunbo Long, Xinping Liu, Zhou Wenjie, Encheng Su, Zihang Zeng, Jiaqi Liu, Jiyao Liu, Junchi Yu, Lihao Liu, Philip Torr, Shixiang Tang, Aoran Wang, Xi Chen
Visual-to-symbolic analytical solution inference from field visualizations.

arXiv 2026[arXiv]

SPD
Guangya Hao, Yitong Shang, Yunbo Long, Zhuokai Zhao, Hanxue Liang
Capability-selective subspace projection for self-policy distillation.

arXiv 2026[arXiv]

HyDRO+
Yunbo Long, Liming Xu, Alexandra Brintrup
Efficient privacy-preserving link prediction through condensed graphs.

Expert Systems with Applications, 2026[arXiv]

Anomaly Detection
Yunbo Long, Zhengyang Ling, Sam Brook, Duncan McFarlane, Alexandra Brintrup
Cost-effective visual anomaly detection with unsupervised learning.

IET Conference Proceedings, 2024[arXiv]

EQ-Negotiator
Yunbo Long, Yuhan Liu, Alexandra Brintrup
Dynamic emotional personas for edge-deployable credit negotiation.

NeurIPS2025@PersonaLLM[arXiv]

Inter-Column Logic
Yunbo Long, Liming Xu, Alexandra Brintrup
Evaluating logical relationships in synthetic tabular data.

ICLR2025@SynData[arXiv]

Awards

Academic Service