TGDC Contact
REF-01 / Primer TGDC

What are RL environments for LLM training?

An RL environment for LLM training is a packaged task world: a task specification, the working state and documents the model interacts with, and a programmatic verifier that scores each attempt. Reinforcement learning then optimises the model against that score.

Three parts
A task, a realistic environment state, a programmatic verifier
Reward
Computed by the verifier, not inferred from human preference
Scarce input
Verifiable tasks drawn from work that actually happened

The three components

Why labs shifted from corpora to environments

Pre-training on static text teaches a model what work looks like. It does not teach the model to do the work, because there is no feedback loop. The current generation of reasoning models is trained heavily with reinforcement learning on verifiable tasks: the model attempts a task many times, the verifier grades each attempt, and the model updates toward strategies that succeed.

That changes what training data means. The bottleneck is no longer tokens; it is verifiable task instances. Maths and code came first because their verifiers are trivial: a proof checks or it doesn't, a test suite passes or it doesn't. The frontier now is everything else: the document-heavy, judgment-heavy work that fills real operations.

What makes an RL environment good

How TGDC builds them

The General Data Company builds RL environments from consented, rights-cleared enterprise sources (insolvency document estates, reenacted expert workflows, and contributed personal documents), anonymised and verified per batch. Because the source material never appeared online, the tasks are genuinely unseen. Each task ships with its own programmatic verifier and a held-out evaluation split, so a lab can measure genuine capability gains rather than memorisation. See RL environments for what a delivery contains, or data licensing for the underlying corpora.