Pith. sign in

REVIEW 9 cited by

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2006.08381 v1 pith:RPPM2D7C submitted 2020-06-15 cs.AI cs.LG

DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning

classification cs.AI cs.LG
keywords languagesconceptsdreamcoderlearningproblemsprogrammingtasksexpertise
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Expert problem-solving is driven by powerful languages for thinking about problems and their solutions. Acquiring expertise means learning these languages -- systems of concepts, alongside the skills to use them. We present DreamCoder, a system that learns to solve problems by writing programs. It builds expertise by creating programming languages for expressing domain concepts, together with neural networks to guide the search for programs within these languages. A ``wake-sleep'' learning algorithm alternately extends the language with new symbolic abstractions and trains the neural network on imagined and replayed problems. DreamCoder solves both classic inductive programming tasks and creative tasks such as drawing pictures and building scenes. It rediscovers the basics of modern functional programming, vector algebra and classical physics, including Newton's and Coulomb's laws. Concepts are built compositionally from those learned earlier, yielding multi-layered symbolic representations that are interpretable and transferrable to new tasks, while still growing scalably and flexibly with experience.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Code as Policies: Language Model Programs for Embodied Control

    cs.RO 2022-09 accept novelty 8.0

    Language models generate robot policy code from natural language commands via few-shot prompting, enabling spatial-geometric reasoning, generalization, and precise control on real robots.

  2. Voyager: An Open-Ended Embodied Agent with Large Language Models

    cs.AI 2023-05 unverdicted novelty 7.0

    Voyager achieves superior lifelong learning in Minecraft by combining an automatic exploration curriculum, a library of executable skills, and iterative LLM prompting with environment feedback, yielding 3.3x more uniq...

  3. Heterogeneous Agent Cohorts for Safe Open-Ended Exploration with Runtime Constraint Memory

    cs.AI 2026-07 conditional novelty 6.0

    Role-specialized LLM cohorts with MCTS-compiled Scars and CAS bandwidth control reach remote sandbox targets with zero executed breaches and lower token cost than homogeneous debate.

  4. Cost-Effective Agent Harnesses for Abstract Reasoning and Generalization on ARC-AGI-1

    cs.AI 2026-07 conditional novelty 6.0

    Explorer-Definer and Reflective Orchestrator harnesses raise DeepSeek V3.2 from 15.5% to 67.25% pass@2 on ARC-AGI-1 public eval at $0.25–$0.62 per task without ARC-specific training.

  5. Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study

    cs.SE 2025-11 unverdicted novelty 6.0

    APIKG4Syn synthesizes API-oriented training data via knowledge graphs and Monte Carlo search to fine-tune a 7B model that reaches 25% pass@1 on HarmonyOS code generation, beating untuned GPT-4o at 17.59%.

  6. How Do Language Models Compose Functions?

    cs.CL 2025-10 conditional novelty 6.0

    LLMs solve compositional factual recall either by computing intermediates or directly, with mechanism choice correlated to translation geometry in embedding spaces.

  7. FactorLibrary: From Polynomials to Circuits via Recursive Subgoals

    cs.LG 2026-06 unverdicted novelty 5.0

    FactorLibrary stores reusable subexpressions to help RL agents (especially PPO+MCTS top-down) find certified optimal arithmetic circuits for polynomials up to complexity 8 at 91.8% success rate.

  8. Explore Before You Solve: The Speed--Depth Trade-off in Epistemic Agents for ARC-AGI-3

    cs.AI 2026-05 unverdicted novelty 5.0

    Public ARC-AGI-3 games are solvable by trivial heuristics, so they fail to test intelligent exploration; the private set is the real test, and an explore-first AERA agent solves 4/25 while baselines solve none.

  9. Artificial Intelligence and the Structure of Mathematics

    cs.AI 2026-04 unverdicted novelty 4.0

    AI agents exploring Platonic mathematical structures via proof hypergraphs may reveal the overall architecture of formal mathematics and what makes parts of it human-accessible.