Skip to content
AI News HubLIVE
Original source2 min read

Induction and Inquiry via Probabilistic Reasoning over Language and Code

Summary

The paper introduces a computational model that encodes symbolic knowledge as mental programs combining natural language and source code, and sequentially infers them using LLM-guided Bayesian learning. Across behavioral studies, the model reproduces quantitative signatures of human inductive learning and active inquiry, such as anchoring and garden-pathing, while pure LLMs and classic Bayesian models either fail, fail to match human behavior, or require exorbitant compute.

SourcearXiv AIAuthor: Wasu Top Piriyakulkij, Sam Acquaviva, Cassidy Langenfeld, Joshua Tenenbaum, Kevin Ellis
Induction and Inquiry via Probabilistic Reasoning over Language and Code
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 1 Sep 2026]

Title:Induction and Inquiry via Probabilistic Reasoning over Language and Code

View a PDF of the paper titled Induction and Inquiry via Probabilistic Reasoning over Language and Code, by Wasu Top Piriyakulkij and 4 other authors

View PDF HTML (experimental)

Abstract:How humans grow and maintain abstract knowledge from the sparse, streaming noisy data of experience is a longstanding challenge in cognitive science. Any computational account must satisfy at least three desiderata: It must be (1) data-efficient and compute-efficient, (2) capture gradations of uncertainty to support intelligent inquiry and information gathering, and (3) be flexible enough to mentally represent the endless range of concepts people can learn and think about. Here we introduce a computational model that captures these three properties, by encoding symbolic knowledge as mental programs that combine natural language with source code, and sequentially inferring mental programs using LLM-guided Bayesian learning algorithms. Across a range of behavioral studies this model successfully reproduces quantitative signatures of human inductive learning and active inquiry, such as anchoring, garden-pathing, and other effects. In contrast, pure LLMs and classic Bayesian models either fail at the underlying task, or do not reproduce human behavior, or succeed only at exorbitant computational cost. These results suggest that one way humans continually grow their knowledge is by mentally representing many hypotheses spanning language-like and program-like representations, then revising those hypotheses to approximate Bayesian updates, while a bottom-up neural mechanism (an LLM) makes inference both tractable and learnable.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2609.01815 [cs.AI]

(or arXiv:2609.01815v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.01815

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Wasu Top Piriyakulkij [view email] [v1] Tue, 1 Sep 2026 19:44:18 UTC (1,281 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Induction and Inquiry via Probabilistic Reasoning over Language and Code, by Wasu Top Piriyakulkij and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Symbolic knowledge is represented as mental programs that blend natural language with source code and are inferred sequentially via LLM-guided Bayesian algorithms.
  • The model targets three desiderata: data and compute efficiency, graded uncertainty for active inquiry, and flexibility to represent unbounded concepts.
  • Behavioral studies show the model reproduces quantitative human signatures including anchoring and garden-pathing effects.
  • Pure LLMs and classic Bayesian models either fail the task, miss human behavior, or succeed only at exorbitant computational cost.

Highlights and analysis are generated automatically and may contain errors. Check the original source.