Learning to Discover at Test Time
Mert Yuksekgonul et al.
arXiv:2601.16175
In short
TTT-Discover keeps training an open LLM with reinforcement learning on a single hard problem at test time, aiming for one excellent solution rather than good average performance. It set new records in maths, GPU kernels, algorithm contests and biology for a few hundred dollars per problem.
Why it matters
Test-time training as a tool for scientific discovery, reproducible with open models.
Read first
The 3 Field Guide ideas this paper leans on.
Starting from scratch? The full route 22 ideas · basics first
- Machine Learning ✓ understood
Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.
- Reinforcement Learning · read first ✓ understood
Learning through interaction with an environment, receiving rewards or penalties to learn optimal behavior policies.
- Natural Language Processing ✓ understood
The field of AI that lets computers read, interpret, translate and generate human language, from spam filters and search to chatbots.
- Token ✓ understood
The unit of text a language model reads and writes: a word, part of a word, or a character, drawn from the model's fixed vocabulary.
- Tokenization ✓ understood
Splitting text into tokens, usually subword pieces, and mapping each to an integer ID so a language model can process it.
- Language Modeling ✓ understood
Assigning probabilities to sequences of text, in practice by predicting each next token from the ones before it; the objective behind large language models.
- Dataset ✓ understood
A collection of data examples used for training, validating, or testing machine learning models.
- Training ✓ understood
The process of fitting a model to data by repeatedly measuring how wrong its outputs are and adjusting its parameters to reduce that error.
- Unsupervised Learning ✓ understood
Learning from unlabeled data to discover hidden patterns, structures, or relationships without explicit target outputs.
- Self-Supervised Learning ✓ understood
Training on unlabeled data by making the data supply its own answers: hide or alter part of an input and have the model predict or match it.
- Pre-training ✓ understood
Training a model on a large dataset (often self-supervised) before fine-tuning on specific tasks, enabling transfer learning.
- Feature ✓ understood
A single measurable property of an example, such as a house's floor area or how many links an email contains, used as an input to a model.
- Neural Network ✓ understood
A model built from layers of simple units, each taking a weighted sum of its inputs and applying a nonlinearity; training adjusts the weights so the whole stack maps inputs to useful outputs.
- Deep Learning ✓ understood
A subset of machine learning that uses neural networks with multiple layers (deep neural networks) to learn hierarchical representations of data.
- Representation Learning ✓ understood
Letting a model learn its own internal description of the data, such as embeddings or layered visual features, instead of relying on features designed by hand.
- Embedding ✓ understood
A list of numbers (a vector) that represents a word, sentence, image or other item, learned so that similar items end up close together.
- Attention Mechanism ✓ understood
A technique that lets a neural network weigh every part of its input when producing each output, focusing on the parts most relevant at that step.
- Transformer ✓ understood
A neural network architecture, introduced in 2017, built from stacked self-attention and feed-forward layers; the basis of nearly every modern large language model.
- Large Language Model · read first ✓ understood
A neural network, almost always a transformer, trained on vast amounts of text to predict the next token, which lets it write, answer, summarize and follow instructions.
- Fine-Tuning ✓ understood
The process of further training a pre-trained model on a specific dataset to adapt it for a particular task or domain.
- Catastrophic Forgetting ✓ understood
The tendency of neural networks to completely forget previously learned information when learning new tasks.
- Continual Learning · read first ✓ understood
Learning new tasks sequentially without forgetting previously learned tasks, addressing catastrophic forgetting.
In the frontier
- Rank
- #77 of 100
- Citations
- 71
- as of Aug 9, 2026
- Published
- Jan 2026
Topics: RL for reasoning , Research automation , Reasoning methods
Selection: 1kpapers.com by Together AI, most-cited as of Aug 9, 2026