---
title: "BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.08177v1"
permalink: "https://feed.astralor.com/items/itm_be40faff6c8173262f42d5c5"
published: "2026-11-05T15:33:32.000Z"
score: 58
channel: "ai"
tags: ["BabyTheorist","Benchmark","Learning","Theorize","World","Observation Alone How","Current"]
---

# BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone

## 速览

How would we know whether a machine truly understands the world? We argue that one key capability is \textit{observational theory learning}: acquiring reusable theories from pure observations and applying them to new si…

## 关键点

- How would we know whether a machine truly understands the world?
- We argue that one key capability is \textit{observational theory learning}: acquiring reusable theories from pure observations and applying them to new situations.
- Current visual reasoning benchmarks focus primarily on the latter, presenting each task as a few-shot puzzle grouped by a common rule.

## 全文

How would we know whether a machine truly understands the world? We argue that one key capability is \textit{observational theory learning}: acquiring reusable theories from pure observations and applying them to new situations. Current visual reasoning benchmarks focus primarily on the latter, presenting each task as a few-shot puzzle grouped by a common rule. We introduce BabyTheorist, a benchmark for controlled training and evaluation of observational theory learning. BabyTheorist generates continual streams of before-after visual observations from hidden compositional programs; during training, learners see only the resulting transitions, with no program labels, task identities, or support sets. To support theory learning and evaluation, BabyTheorist controls the program language, a curriculum over program complexity, recurring frequent subprograms, and a continual train-test protocol with level skipping. Seven representative baselines plateau well below ceiling, with the gap widening as the curriculum advances---evidence that BabyTheorist isolates a capability current program-learning approaches do not yet address.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_be40faff6c8173262f42d5c5