Results 291 to 300 of about 1,501,850 (327)

DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning

International Conference on Machine Learning
In this work, we investigate the potential of large language models (LLMs) based agents to automate data science tasks, with the goal of comprehending task requirements, then building and training the best-fit machine learning models.
Siyuan Guo, Cheng Deng, Ying Wen, Hechang Chen, Yi Chang, Jun Wang   +5 more
semanticscholar   +1 more source

A Case Study of LLM for Automated Vulnerability Repair: Assessing Impact of Reasoning and Patch Validation Feedback

AIware
Recent work in automated program repair (APR) proposes the use of reasoning and patch validation feedback to reduce the semantic gap between the LLMs and the code under analysis.
Ummay Kulsum, Haotian Zhu, Bowen Xu, Marcelo d’Amorim   +3 more
semanticscholar   +1 more source

LLM-ARC: Enhancing LLMs with an Automated Reasoning Critic

arXiv.org
We introduce LLM-ARC, a neuro-symbolic framework designed to enhance the logical reasoning capabilities of Large Language Models (LLMs), by combining them with an Automated Reasoning Critic (ARC).
Aditya Kalyanpur, K. Saravanakumar, Victor Barres, Jennifer Chu-Carroll, David O. Melville, David Ferrucci   +5 more
semanticscholar   +1 more source

Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS

arXiv.org
In-context learning (ICL) enables large language models (LLMs) to perform downstream tasks through advanced prompting and high-quality demonstrations.
Jinyang Wu, Mingkuan Feng, Shuai Zhang, Feihu Che, Zengqi Wen, Jianhua Tao   +5 more
semanticscholar   +1 more source

Theory-Specific Automated Reasoning

2010
In designing a large-scale computerized proof system, one is often confronted with issues of two kinds: issues regarding an underlying logical calculus, and issues that refer to theories, either specified axiomatically or characterized by indication of either a privileged model or a family of intended models. Proof services related to the theories most
Formisano A., OMODEO, EUGENIO
openaire   +5 more sources

Learning Guided Automated Reasoning: A Brief Survey

Logics and Type Systems in Theory and Practice
Automated theorem provers and formal proof assistants are general reasoning systems that are in theory capable of proving arbitrarily hard theorems, thus solving arbitrary problems reducible to mathematics and logical reasoning. In practice, such systems
Lasse Blaauwbroek, David M. Cerna, Thibault Gauthier, Jan Jakubruv, C. Kaliszyk, Martin Suda, Josef Urban   +6 more
semanticscholar   +1 more source

An overview of automated reasoning

IEEE Transactions on Systems, Man, and Cybernetics, 1990
Two general approaches to reasoning with imperfect information are discussed: nonmonotonic reasoning and a calculus of uncertainty. Default reasoning is posed as an approach that is potentially capable of integrating many facets of these two approaches. Practical requirements for default reasoning are then established.
S. Post, A.P. Sage
openaire   +2 more sources

Automated Reasoning and Knowledge Inference on OPC UA Information Models

Industrial Cyber-Physical Systems, 2019
The fourth industrial revolution demands flexibility, adaptability, transparency and semantic interoperability. Within the German Industry 4.0 initiative, the Reference Architecture Model Industrie 4.0 (RAMI4.0) has recently been standardized and OPC ...
Jupiter Bakakeu, M. Brossog, J. Zeitler, J. Franke, S. Tolksdorf, H. Klos, J. Peschke   +6 more
semanticscholar   +1 more source

Automating Automated Reasoning

2019
The vision of automated support for the investigation of logics, proposed decades ago, has been implemented in many forms, producing numerous tools that analyze various logical properties (e.g., cut-elimination, semantics, and more). However, full ‘automation of automated reasoning’ in the sense of automatic generation of efficient provers has remained
Zohar, Yoni, Tishkovsky, Dmitry, Schmidt, Renate A., Zamansky, Anna   +3 more
openaire   +3 more sources

ProcessBench: Identifying Process Errors in Mathematical Reasoning

Annual Meeting of the Association for Computational Linguistics
As language models regularly make mistakes when solving math problems, automated identification of errors in the reasoning process becomes increasingly significant for their scalable oversight.
Chujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, Junyang Lin   +8 more
semanticscholar   +1 more source