paper-with-me

Papers

Neural-guided, Bidirectional Program Search for Abstraction and Reasoning

2021-10-22 · Simon Alford, Anshula Gandhi, Akshay Rangamani, Andrzej Banburski, Tony Wang, Sylee Dandekar, John Chin, Tomaso Poggio, Peter Chin

One of the challenges facing artificial intelligence research today is designing systems capable of utilizing systematic reasoning to generalize to new tasks. The Abstraction and Reasoning Corpus (ARC) measures such a capability through a set of visual reasoning tasks. In this paper we report incremental progress on ARC and lay the foundations for two approaches to abstraction and reasoning not based in brute-force search. We first apply an existing program synthesis system called DreamCoder to create symbolic abstractions out of tasks solved so far, and show how it enables solving of progressively more challenging ARC tasks. Second, we design a reasoning algorithm motivated by the way humans approach ARC. Our algorithm constructs a search graph and reasons over this graph structure to discover task solutions. More specifically, we extend existing execution-guided program synthesis approaches with deductive reasoning based on function inverse semantics to enable a neural-guided bidirectional search algorithm. We demonstrate the effectiveness of the algorithm on three domains: ARC, 24-Game tasks, and a 'double-and-add' arithmetic puzzle.

📄 PDF Abstract BibTeX arXiv:2110.11536

Code (0)

등록된 구현이 없습니다.

Tasks

ARCProgram SynthesisVisual Reasoning

Similar Papers 제목 키워드 기반

Leveraging Language to Learn Program Abstractions and Search Heuristics

2021-06-18 · Catherine Wong, Kevin Ellis, Joshua B. Tenenbaum, Jacob Andreas

Inductive program synthesis, or inferring programs from examples of desired behavior, offers a general paradigm for building interpretable, robust, and generalizable machine learning systems. Effective program synthesis …

Program Synthesis

From Perception to Programs: Regularize, Overparameterize, and Amortize

2022-06-13 · Hao Tang, Kevin Ellis

Toward combining inductive reasoning with perception abilities, we develop techniques for neurosymbolic program synthesis where perceptual input is first parsed by neural nets into a low-dimensional interpretable represe…

Program Synthesis

ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Models

2025-02-13 · R. Kenny Jones, Paul Guerrero, Niloy J. Mitra, Daniel Ritchie

We present ShapeLib, the first method that leverages the priors of LLMs to design libraries of programmatic 3D shape abstractions. Our system accepts two forms of design intent: text descriptions of functions to include …

Synthetic Data Generation

Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus

2022-10-18 · Yudong Xu, Elias B. Khalil, Scott Sanner

The Abstraction and Reasoning Corpus (ARC) aims at benchmarking the performance of general artificial intelligence algorithms. The ARC's focus on broad generalization and few-shot learning has made it difficult to solve …

ARCBenchmarkingFew-Shot LearningProgram Synthesis

Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2

2026-03-20 · Yu-Ning Qiu, Lin-Feng Zou, Jiong-Da Wang, Xue-Rong Yuan 외 arxiv

In high-complexity abstract reasoning, a system must infer a latent rule from a few examples or structured observations and apply it to unseen instances. LLMs can express such rules as programs, but ordinary conversation…