English
Related papers

Related papers: Learning to Solve Abstract Reasoning Problems with…

200 papers

Large language models (LLMs) continue to face challenges in reliably solving reasoning tasks, particularly those that require precise rule following, as often found in mathematical reasoning. This paper introduces a novel neurosymbolic…

Machine Learning · Computer Science 2025-11-19 Varun Dhanraj , Chris Eliasmith

Algorithm extraction aims to synthesize executable programs directly from models trained on algorithmic tasks, enabling de novo algorithm discovery without relying on human-written code. However, applying this paradigm to Transformer is…

Machine Learning · Computer Science 2026-03-20 Yifan Zhang , Wei Bi , Kechi Zhang , Dongming Jin , Jie Fu , Zhi Jin

Recent advances in large language models (LLMs) have given rise to powerful coding agents, making it possible for code assistants to evolve into code engineers. However, existing methods still face significant challenges in achieving…

Software Engineering · Computer Science 2025-12-10 Zongwei Li , Zhonghang Li , Zirui Guo , Xubin Ren , Chao Huang

The recently released GPT-4 Code Interpreter has demonstrated remarkable proficiency in solving challenging math problems, primarily attributed to its ability to seamlessly reason with natural language, generate code, execute code, and…

Computation and Language · Computer Science 2023-10-06 Ke Wang , Houxing Ren , Aojun Zhou , Zimu Lu , Sichun Luo , Weikang Shi , Renrui Zhang , Linqi Song , Mingjie Zhan , Hongsheng Li

Reactive synthesis, the problem of automatically constructing a hardware circuit from a logical specification, is a long-standing challenge in formal verification. It is elusive for two reasons: It is algorithmically hard, and writing…

Recent advancements in deep learning have actively addressed complex challenges within the Computer-Aided Design (CAD) domain.However, most existing approaches rely on task-specifi c models requiring structural modifi cations for new tasks,…

Machine Learning · Computer Science 2026-03-03 Mingi Kim , Yongjun Kim , Jungwoo Kang , Hyungki Kim

Formal analysis to ensure adherence of software to defined architectural constraints is not yet broadly used within software development, due to the effort involved in defining formal architecture models. Within this paper, we outline…

Software Engineering · Computer Science 2025-03-21 Steffen Herbold , Christoph Knieke , Andreas Rausch , Christian Schindler

The predominant approach to visual question answering (VQA) relies on encoding the image and question with a "black-box" neural encoder and decoding a single token as the answer like "yes" or "no". Despite this approach's strong…

Computation and Language · Computer Science 2020-11-24 Weixin Liang , Feiyang Niu , Aishwarya Reganti , Govind Thattai , Gokhan Tur

A generally intelligent learner should generalize to more complex tasks than it has previously encountered, but the two common paradigms in machine learning -- either training a separate learner per task or training a single learner for all…

Machine Learning · Computer Science 2019-05-09 Michael B. Chang , Abhishek Gupta , Sergey Levine , Thomas L. Griffiths

Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when guided only through natural language prompts. We introduce TreeCoder, the most general and…

Machine Learning · Computer Science 2026-04-27 Henrijs Princis , Arindam Sharma , Cristina David

Code generation, defined as automatically writing a piece of code to solve a given problem for which an evaluation function exists, is a classic hard AI problem. Its general form, writing code using a general language used by human…

Artificial Intelligence · Computer Science 2020-07-29 Jacques Basaldúa

Creating and understanding art has long been a hallmark of human ability. When presented with finished digital artwork, professional graphic artists can intuitively deconstruct and replicate it using various drawing tools, such as the line…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Qi Bing , Chaoyi Zhang , Weidong Cai

We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing…

Machine Learning · Computer Science 2025-07-15 Zhangchen Xu , Yang Liu , Yueqin Yin , Mingyuan Zhou , Radha Poovendran

Despite recent success in large language model (LLM) reasoning, LLMs struggle with hierarchical multi-step reasoning tasks like generating complex programs. For these tasks, humans often start with a high-level algorithmic design and…

Computation and Language · Computer Science 2023-05-30 Eric Zelikman , Qian Huang , Gabriel Poesia , Noah D. Goodman , Nick Haber

In the ongoing quest for hybridizing discrete reasoning with neural nets, there is an increasing interest in neural architectures that can learn how to solve discrete reasoning or optimization problems from natural inputs, a task that Large…

Artificial Intelligence · Computer Science 2025-12-19 Marianne Defresne , Romain Gambardella , Sophie Barbe , Thomas Schiex

Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…

Machine Learning · Computer Science 2025-10-28 Amal Abed , Ivan Lukic , Jörg K. H. Franke , Frank Hutter

Analogical reasoning is a hallmark of human intelligence, enabling us to solve new problems by transferring knowledge from one situation to another. Yet, developing artificial intelligence systems capable of robust human-like analogical…

Machine Learning · Computer Science 2026-04-09 Philipp Hellwig , Willem Zuidema , Claire E. Stevenson , Martha Lewis

While sequence-to-sequence models have shown remarkable generalization power across several natural language tasks, their construct of solutions are argued to be less compositional than human-like generalization. In this paper, we present…

Computation and Language · Computer Science 2019-06-07 Kris Korrel , Dieuwke Hupkes , Verna Dankers , Elia Bruni

Intermediate reasoning or acting steps have successfully improved large language models (LLMs) for handling various downstream natural language processing (NLP) tasks. When applying LLMs for code generation, recent works mainly focus on…

Computation and Language · Computer Science 2024-06-25 Tao Sun , Linzheng Chai , Jian Yang , Yuwei Yin , Hongcheng Guo , Jiaheng Liu , Bing Wang , Liqun Yang , Zhoujun Li

Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems.…