Research

Test-Time Training

1 report

Surveys

Test-Time Training: A Survey of Learning at Inference, from Self-Supervision to Memory Layers, LLMs and Agents

Test-time training lets a model keep learning after deployment by optimizing an explicit objective on the test input, context, problem or stream. This survey of 605 papers organizes the field by what is learned at test time and from which signal — self-supervised TTT, TTT layers and test-time memory, LLM test-time training, test-time RL, and agents and robots — writes them in one notation, and weighs five open debates.