# Learning-To-Measure: In-Context Active Feature Acquisition

arXiv: https://arxiv.org/abs/2510.12624 · HTML: https://mlsanity.com/paper/2510.12624/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 62 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Conditional Neural Processes](https://mlsanity.com/paper/1807.01613/) (2018)
- [Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables](https://mlsanity.com/paper/1903.08254/) (2019)
- [Transformers Can Do Bayesian Inference](https://mlsanity.com/paper/2112.10510/) (2021)
- [Monte Carlo Gradient Estimation in Machine Learning](https://mlsanity.com/paper/1906.10652/) (2019)
- [Supervised Pretraining Can Learn In-Context Reinforcement Learning](https://mlsanity.com/paper/2306.14892/) (2023)
- [Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling](https://mlsanity.com/paper/2207.04179/) (2022)
- [EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE](https://mlsanity.com/paper/1809.11142/) (2018)
- [Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining](https://mlsanity.com/paper/2310.08566/) (2023)
- [Large Scale Transfer Learning for Tabular Data via Language Modeling](https://mlsanity.com/paper/2406.12031/) (2024)
- [Statistical Foundations of Prior-Data Fitted Networks](https://mlsanity.com/paper/2305.11097/) (2023)
- [Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models](https://mlsanity.com/paper/2007.00163/) (2020)
- [Learning to Maximize Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2301.00557/) (2023)
- [Active Feature Acquisition with Generative Surrogate Models](https://mlsanity.com/paper/2010.02433/) (2020)
- [Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data](https://mlsanity.com/paper/2507.03971/) (2025)
- [Classification with Costly Features using Deep Reinforcement Learning](https://mlsanity.com/paper/1711.07364/) (2017)
- [Identifiable Generative Models for Missing Not at Random Data Imputation](https://mlsanity.com/paper/2110.14708/) (2021)
- [Interpretable by Design: Learning Predictors by Composing Interpretable Queries](https://mlsanity.com/paper/2207.00938/) (2022)
- [Full Law Identification In Graphical Models Of Missing Data: Completeness Results](https://mlsanity.com/paper/2004.04872/) (2020)
- [Variational Information Pursuit for Interpretable Predictions](https://mlsanity.com/paper/2302.02876/) (2023)
- [Estimating Conditional Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2306.03301/) (2023)
- [Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams](https://mlsanity.com/paper/1901.00243/) (2019)
- [Empirical Frequentist Coverage of Deep Learning Uncertainty Quantification Procedures](https://mlsanity.com/paper/2010.03039/) (2020)
- [Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo](https://mlsanity.com/paper/2202.04599/) (2022)
- [Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement](https://mlsanity.com/paper/2410.11448/) (2024)

## Built on by (most cited first, 5 of 5)

- [Zero-Shot Active Feature Acquisition via LLM-Elicitation](https://mlsanity.com/paper/2606.18933/) (2026)
- [Wide Learning: Learning to Reach Evidence](https://mlsanity.com/paper/2608.29608/) (2026)
- [When Does Test-Time Physical Diagnosis Pay? A Frozen Policy Buys Evidence It Never Reads](https://mlsanity.com/paper/2609.22299/) (2026)
- [Active Feature Acquisition With Incomplete Training Data](https://mlsanity.com/paper/2609.32325/) (2026)
- [Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition](https://mlsanity.com/paper/2610.03454/) (2026)

## Abstract (arXiv)

Active feature acquisition (AFA) is a sequential decision-making problem where the goal is to improve model performance for test instances by adaptively selecting which features to acquire. In practice, AFA methods often learn from retrospective data with systematic missingness in the features and limited task-specific labels. Most prior work addresses acquisition for a single predetermined task, limiting scalability. To address this limitation, we formalize the meta-AFA problem, where the goal is to learn acquisition policies across various tasks. We introduce Learning-to-Measure (L2M), which consists of i) reliable uncertainty quantification over unseen tasks, and ii) an uncertainty-guided greedy feature acquisition agent that maximizes conditional mutual information. We demonstrate a sequence-modeling or autoregressive pre-training approach that underpins reliable uncertainty quantification for tasks with arbitrary missingness. L2M operates directly on datasets with retrospective missingness and performs the meta-AFA task in-context, eliminating per-task retraining. Across synthetic and real-world tabular benchmarks, L2M matches or surpasses task-specific baselines, particularly under scarce labels and high missingness.