WhoBuilt

Tiny Recursive Model

Also known as TRM, TRMs, tiny recursive models

1 Talk5 Facts5 Sources

Key facts

Capabilities
Can learn to solve tasks without chain-of-thought supervision
Uses truncated backpropagation through one full recursion loop
Shares one network across low-level and high-level processing while keeping separate latent states

From talks

Results and examples shared in single talks

Timeline 3

Dated events, newest first. Open the sources under any item.

How we verify
20263 events
  1. as of May 2026Capability
    Can learn to solve tasks without chain-of-thought supervision
    “It's able to discover things without being teacher-forced via chain of thought.” 27:20
    Unverified1 source· Talk
  2. as of May 2026Capability
    Uses truncated backpropagation through one full recursion loop
    “Rather than going through just one call to the H-net and the L-net, it goes through one full recursion loop.” 22:05
    Unverified1 source· Talk
  3. as of May 2026Capability
    Shares one network across low-level and high-level processing while keeping separate latent states
    “You share weights between the L-net and the H-net, and it's just called the net.” 23:25
    Unverified1 source· Talk

Talks 1

37:53
Recursion Is The Next Scaling Law In AI
François Chollet, Wa C

The talk explains how recursion can give AI models more reasoning depth at inference time without requiring more parameters. It compares hierarchical reasoning models (HRM) with tiny recursive models (TRM), highlighting repeated refinement of latent states and truncated backpropagation as key ideas. The speakers argue that these methods can solve tasks such as Sudoku and ARC with small, task-specific models, without step-by-step reasoning traces. They close by suggesting that recursive reasoning could complement the broad representations learned by large language models.

May 1, 2026· 38 minDiscussed 0:00