Related papers: Fast and flexible: Human program induction in abst…
Large language models are increasingly deployed as research agents for deep search and long-horizon information seeking, yet their performance often degrades as interaction histories grow. This degradation, known as context rot, reflects a…
Recent advancements in Large Language Models (LLMs) have generated growing interest in their structured reasoning capabilities, particularly in tasks involving abstraction and pattern recognition. The Abstraction and Reasoning Corpus (ARC)…
The Abstraction and Reasoning Corpus (ARC) poses a significant challenge to artificial intelligence, demanding broad generalization and few-shot learning capabilities that remain elusive for current deep learning methods, including large…
In the pursuit of artificial general intelligence (AGI), we tackle Abstraction and Reasoning Corpus (ARC) tasks using a novel two-pronged approach. We employ the Decision Transformer in an imitation learning paradigm to model human…
The AI2 Reasoning Challenge (ARC), a new benchmark dataset for question answering (QA) has been recently released. ARC only contains natural science questions authored for human exams, which are hard to answer and require advanced logic…
The Abstraction and Reasoning Corpus (ARC) tests AI systems' ability to perform human-like inductive reasoning from a few demonstration pairs. Existing Gymnasium-based RL environments severely limit experimental scale due to computational…
Abstraction reasoning is a long-standing challenge in artificial intelligence. Recent studies suggest that many of the deep architectures that have triumphed over other domains failed to work well in abstract reasoning. In this paper, we…
Causal induction, i.e., identifying unobservable mechanisms that lead to the observable relations among variables, has played a pivotal role in modern scientific discovery, especially in scenarios with only sparse and limited data. Humans,…
Abstract reasoning from minimal examples remains a core unsolved problem for frontier foundation models such as GPT-5 and Grok 4. These models still fail to infer structured transformation rules from a handful of examples, which is a key…
Inductive program synthesis, or programming by example, requires synthesizing functions from input-output examples that generalize to unseen inputs. While large language model agents have shown promise in programming tasks guided by natural…
Analytical reasoning is an essential and challenging task that requires a system to analyze a scenario involving a set of particular circumstances and perform reasoning over it to make conclusions. In this paper, we study the challenge of…
Abstract Visual Reasoning (AVR) problems are commonly used to approximate human intelligence. They test the ability of applying previously gained knowledge, experience and skills in a completely new setting, which makes them particularly…
The Abstraction and Reasoning Corpus (ARC-AGI) probes few-shot abstraction and rule induction on small visual grids, but progress is difficult to measure on static collections of hand-authored puzzles due to overfitting, dataset leakage,…
The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) is a generative, few-shot fluid intelligence benchmark. Although humans effortlessly solve ARC-AGI, it remains extremely difficult for even the most advanced…
Reasoning requires going beyond pattern matching or memorization of solutions to identify and implement "algorithmic procedures" that can be used to deduce answers to hard problems. Doing so requires realizing the most relevant primitives,…
Learning internal reasoning processes is crucial for developing AI systems capable of sustained adaptation in dynamic real-world environments. However, most existing approaches primarily emphasize learning task-specific outputs or static…
The IPARC Challenge, inspired by ARC, provides controlled program synthesis tasks over synthetic images to evaluate automatic program construction, focusing on sequence, selection, and iteration. This set of 600 tasks has resisted automated…
When learning an input-output mapping from very few examples, is it better to first infer a latent function that explains the examples, or is it better to directly predict new test outputs, e.g. using a neural network? We study this…
Humans flexibly solve new problems that differ qualitatively from those they were trained on. This ability to generalize is supported by learned concepts that capture structure common across different problems. Here we develop a…
We present the ARC-DA dataset, a direct-answer ("open response", "freeform") version of the ARC (AI2 Reasoning Challenge) multiple-choice dataset. While ARC has been influential in the community, its multiple-choice format is…