# The Surprising Effectiveness of Test-Time Training for Few-Shot Learning

arXiv: https://arxiv.org/abs/2411.07279 · HTML: https://mlsanity.com/paper/2411.07279/

## Key facts

- Cited by 96 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 43 references that are in the map.
- First posted on arXiv 11 Nov 2024.

## Builds on (most cited first, 30 of 31)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [What learning algorithm is in-context learning? Investigations with linear models](https://mlsanity.com/paper/2211.15661/) (2022)
- [MetaICL: Learning to Learn In Context](https://mlsanity.com/paper/2110.15943/) (2021)
- [Learning to (Learn at Test Time): RNNs with Expressive Hidden States](https://mlsanity.com/paper/2407.04620/) (2024)
- [Function Vectors in Large Language Models](https://mlsanity.com/paper/2310.15213/) (2023)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [Test-Time Training with Masked Autoencoders](https://mlsanity.com/paper/2209.07522/) (2022)
- [Hypothesis Search: Inductive Reasoning with Language Models](https://mlsanity.com/paper/2309.05660/) (2023)
- [Test-Time Training on Nearest Neighbors for Large Language Models](https://mlsanity.com/paper/2305.18466/) (2023)
- [Learning How Hard to Think: Input-Adaptive Allocation of LM Computation](https://mlsanity.com/paper/2410.04707/) (2024)
- [Combining Induction and Transduction for Abstract Reasoning](https://mlsanity.com/paper/2411.02272/) (2024)
- [Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs](https://mlsanity.com/paper/2410.08020/) (2024)
- [Communicating Natural Programs to Humans and Machines](https://mlsanity.com/paper/2106.07824/) (2021)
- [Addressing the Abstraction and Reasoning Corpus via Procedural Example Generation](https://mlsanity.com/paper/2404.07353/) (2024)
- [H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark](https://mlsanity.com/paper/2409.01374/) (2024)
- [CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay](https://mlsanity.com/paper/2402.04858/) (2024)
- [Probing the Decision Boundaries of In-context Learning in Large Language Models](https://mlsanity.com/paper/2406.11233/) (2024)
- [Neural networks for abstraction and reasoning: Towards broad generalization in machines](https://mlsanity.com/paper/2402.03507/) (2024)
- [Solving ARC visual analogies with neural embeddings and vector arithmetic: A generalized method](https://mlsanity.com/paper/2311.08083/) (2023)

## Built on by (most cited first, 30 of 96)

- [Reinforcement Learning via Self-Distillation](https://mlsanity.com/paper/2601.20802/) (2026)
- [Self-Adapting Language Models](https://mlsanity.com/paper/2506.10943/) (2025)
- [Nested Learning: The Illusion of Deep Learning Architectures](https://mlsanity.com/paper/2512.24695/) (2025)
- [Aristotle: IMO-level Automated Theorem Proving](https://mlsanity.com/paper/2510.01346/) (2025)
- [Training a Scientific Reasoning Model for Chemistry](https://mlsanity.com/paper/2506.17238/) (2025)
- [Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles](https://mlsanity.com/paper/2505.23590/) (2025)
- [Self-Improving LLM Agents at Test-Time](https://mlsanity.com/paper/2510.07841/) (2025)
- [ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory](https://mlsanity.com/paper/2509.04439/) (2025)
- [SIA: Self Improving AI with Harness & Weight Updates](https://mlsanity.com/paper/2605.27276/) (2026)
- [Test-Time Adaptation for LLM Agents via Environment Interaction](https://mlsanity.com/paper/2511.04847/) (2025)
- [AdaJEPA: An Adaptive Latent World Model](https://mlsanity.com/paper/2606.32026/) (2026)
- [FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training](https://mlsanity.com/paper/2501.09213/) (2025)
- [TTCS: Test-Time Curriculum Synthesis for Self-Evolving](https://mlsanity.com/paper/2601.22628/) (2026)
- [SLOT: Sample-specific Language Model Optimization at Test-time](https://mlsanity.com/paper/2505.12392/) (2025)
- [Let's (not) just put things in Context: Test-Time Training for Long-Context LLMs](https://mlsanity.com/paper/2512.13898/) (2025)
- [Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale](https://mlsanity.com/paper/2604.18572/) (2026)
- [Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement](https://mlsanity.com/paper/2505.07961/) (2025)
- [Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos](https://mlsanity.com/paper/2507.12646/) (2025)
- [DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning](https://mlsanity.com/paper/2505.19850/) (2025)
- [Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs](https://mlsanity.com/paper/2510.17472/) (2025)
- [Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training](https://mlsanity.com/paper/2603.12255/) (2026)
- [Learning to Reason from Feedback at Test-Time](https://mlsanity.com/paper/2502.15771/) (2025)
- [ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus](https://mlsanity.com/paper/2511.00162/) (2025)
- [Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging](https://mlsanity.com/paper/2505.14136/) (2025)
- [Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting](https://mlsanity.com/paper/2506.00635/) (2025)
- [LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space](https://mlsanity.com/paper/2509.24771/) (2025)
- [Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning](https://mlsanity.com/paper/2510.04786/) (2025)
- [Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People](https://mlsanity.com/paper/2510.20886/) (2025)
- [Tool Verification for Test-Time Reinforcement Learning](https://mlsanity.com/paper/2603.02203/) (2026)
- [From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models](https://mlsanity.com/paper/2506.07280/) (2025)

## Abstract (arXiv)

Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks even when given a small number of in-context task examples. We investigate the effectiveness of test-time training (TTT) -- temporarily updating model parameters during inference using a loss derived from input data -- as a mechanism for improving LMs' reasoning and few-shot learning capabilities. On the Abstraction and Reasoning Corpus (ARC), performing TTT with in-context examples yields up to 6× higher accuracy compared to fine-tuned baselines -- reaching 53.0% on the public validation set with an 8B-parameter LM and 61.9% when ensembled with program-synthesis methods, matching average human performance. On BIG-Bench Hard (BBH), TTT on in-context examples surpasses standard few-shot prompting in the 10-shot setting by 7.3 percentage points (50.5% to 57.8%). Our findings highlight the limitations of in-context learning for novel tasks and demonstrate the potential of test-time training to enhance language model adaptability.