Aligning Long-Horizon AI Agents
AI agents drift from human intent over long-horizon tasks.
We infer their plans with uncertainty-aware representations to keep humans in the loop.
Funders
Previous funding
Funded by ARIA, the UK's high-risk, high-reward research agency.
2025, under the Safeguarded AI programme.
Our Team
Director of Recursive Safeguarding Ltd
Oxford Univ ARIA SGAI TA1 & Opportunity Seed
Finishing DPhil at Oxford; formerly at Mila (worked with Yoshua Bengio)
Worked on LLM hallucinations at Cohere
Technical Cofounder and CTO of RightPick
Nanyang Asst Professor & NRF-AI Fellow, NTU Singapore
Cofounder and Director of Quro Medical
Formerly Oxford Univ Nightingale Fellow
Machine Learning Researcher (computational statistics, deep generative modeling, causal inference)
Oxford Univ Professor
ARIA SGAI TA1 grants & Opportunity Seed (SynthStats: GFlowNet-finetuning)
ERC Consolidator Grant BLAST: Better Languages for Statistics
Faculty at Bath Univ
Expert in programming language theory
Expert in formal verification and categorical semantics
Oxford Univ PhD student in AI and theory
SERI MATS scholar and OpenPhil funded
Published work on probabilistic programming and RL safety
Independent researcher and entrepreneur
Anthropic collaborator (Exa-scale Safeguards)
Formerly Mila: Scientist AI with Yoshua Bengio
Co-founded Alignment at TII (Falcon, the #1 LLM)
Previous EdTech startup co-founder, exited
Oxford Univ postdoc
Projects with ARIA SGAI TA1 through Oxford and Adjoint Labs Ltd
Leading contributor to Markov category theory
Tech and start-up background (Munich, Oxford, Cambridge)
Advisory board of Smith School of Enterprise and the Environment
Contact
For research collaborations, institutional partnerships, grant or programme funding, or prospective research roles, email us or use the form below.
Contact the team
Or email us directly at