cognitive training
the paradigm: a self-improvement loop where a model creates its own training tasks, keeps the ones worth creating, and learns from them
xent — a transparent
path to AGI
xent is an AI research lab: we improve the cognitive abilities of language models — transparently, toward artificial general intelligence
the idea is cognitive training: a model discovers relevant new skills by creating tasks for itself — with a principled way to measure which tasks are worth creating
done right, this turns a language model into a self-improving system that stays stable and competitive at the same time
what we build
one research program, three concrete parts
xent games
the task space: a surprisingly rich family of games a model can pose to itself and score using nothing but its own probabilities
frost
the algorithm: our reinforcement-learning method, exploiting the differentiable structure of xent games to learn faster than Monte-Carlo methods
how it works
instead of an ever-growing pile of handcrafted environments, cognitive training turns task discovery itself into a measurable loop:
- create — the model proposes a new , drawing on knowledge already implicit in its own distribution
- measure — the values the game by its transfer: how well it captures existing skills while opening genuinely new ones
- train — learns the worthwhile games efficiently
- repeat — the model returns to task creation stronger, and better at discovering what to learn next
counterfactual thinking — try it
one family of xent games asks: which piece of information would most change one's view? here is the human-scale version —
“a new language model improved by 40% on its main benchmark.”
which new fact should change your interpretation the most?
an illustration for visitors — the real games are played, and scored, by the model itself.
our research
the xent games — “Cross-Entropy Games for Language Models”
introduces the task space: games grounded in a model's own measures, from in-filling to counterfactual thinking
cognitive training — “Cognitive Training for Language Models”
formulates the self-improvement loop and derives the meta-objective that decides which games are worth creating
frost — “Cross-Entropy Games and Frost Training”
the training algorithm: exploiting differentiable game structure to move beyond the Monte-Carlo paradigm
notes — Clément's running notes on the xent games at xent.blog
the people building xent
Franck Gabriel
researcher · associate professor at Université Claude Bernard Lyon 1
website
linkedin
Clément and Franck, with Arthur Jacot, received the 2026 Frontiers of Science Award for the neural tangent kernel — a mathematical foundation of modern deep learning
contact — write to hello@xent.io
the territory
this page is one path through xent's ideas. the map holds all of them — thirteen concepts, connected the way the ideas actually are.