Research, at a glance
Artificial life
Symbolic reasoning in embodied agents
Living matter
Steering biobots with language
Embodied agents
Language-driven control, in a body
Artificial life
Flocks that reproduce as units
Computational intelligence
Learning, evolution, and the Baldwin effect
Markets
Finding the phase boundary in price
Embodied agents
A physical Braitenberg vehicle
Coming soon
Computational intelligence
Evolving free-energy self-modelling networks
Coming soon
Postdoctoral Research Fellow · University of Vermont
Nam H. Le.
I study phase transitions in complex adaptive systems — in living matter, and in markets.
Evolutionary computation, artificial life, and the language-driven control of living and embodied systems. The same question runs through everything I build: how does coherent, adaptive behaviour arise from parts that have no plan — and once it has arisen, can we steer it?
One question, several substrates
A flock of cells and a market are both collectives of parts that adapt to one another without a plan. In both, the interesting events are not the averages but the transitions — the moment a population commits to a new organisation, the moment a regime turns over. My work is about characterising those transitions well enough to detect them, and in the case of living matter, well enough to cause them.
The methods travel across them: evolutionary computation, dynamical-systems analysis, and — more recently — foundation models used not as oracles but as interfaces, translating human intent into interventions on a system that has no notion of what we want.
Selected work
- 2026
Who Pays for the Knowledge Models Copy? Model Collapse as Rogers' Paradox
Language models trained on each other's output forget, rare knowledge first — the same trap cultural evolution calls Rogers' paradox, and the same way out: someone has to keep learning for themselves.
Zenodo
- 2026
Oddworld: Relational Reasoning Emerges under Implicit Selection in Evolving Attention Agents
An evolved attention network — its weights are the genome — learns to spot the odd one out, with no fitness function ever scoring accuracy.
Zenodo
- 2025
Emergent Collective Reproduction via Evolving Neuronal Flocks
Neural agents self-organise into flocks that divide — an evolutionary transition in individuality, arrived at without being asked for.
Northeast Journal of Complex Systems
- 2025
Decoupling Representation and Learning in Genetic Programming
The LaSER approach: let the program describe the representation and let a learner do the fitting.
GPTP · arXiv:2505.17309
- 2025
Giving Simulated Cells a Voice
Evolving prompt-to-intervention models for cellular control.
GECCO Companion, ACM