Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks
Katherine M. Collins, Catherine Wong, Jiahai Feng, Megan Wei, Joshua B. Tenenbaum
CommentsThis update clarifies the theoretical architecture by separating Regulation as the Soft Symbolic Control layer from Control as a deterministic runtime engine, while adding explicit discussion of how the current implementation should be interpreted in light of that distinction
CommentsAccepted for publication in the Proceedings of the 30th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2026)
Symbolic Intermediaries as a Linguistic-Numerical Interface for LLM-Driven Geometric Reasoning
符号中介作为LLM驱动几何推理的语言-数值接口
João Pedro Gandarela, Thiago Rios, Stefan Menzel, André Freitas
机构
*
Idiap Research Institute(Idiap研究 institute)
;
École Polytechnique Fédérale de Lausanne(瑞士联邦理工学院)
;
Honda Research Institute Europe(本田欧洲研究院)
;
Department of Computer Science, University of Manchester(曼彻斯特大学计算机科学系)
;
National Biomarker Centre, CRUK-MI, University of Manchester(曼彻斯特大学国家生物标记中心)
Tracing the ongoing emergence of human-like reasoning in Large Language Models
追踪大型语言模型中类人推理的持续涌现
Paolo Morosi, Nikoleta Pantelidou, Fritz Günther, Elena Pagliarini, Evelina Leivada
机构
*
Departament de Filologia Catalana, Universitat Autònoma de Barcelona(加泰罗尼亚语言系系,巴塞罗那自治大学)
;
Institut für Psychologie, Humboldt-Universitat zu Berlin(柏林洪堡大学心理学研究所)
;
Institució Catalana de Recerca i Estudis Avançats (ICREA)(加泰罗尼亚高级研究与高级教育研究所)
In Context Learning and Reasoning for Symbolic Regression with Large Language Models
在大型语言模型中进行上下文学习和推理以实现符号回归
Samiha Sharlin, Tyler R. Josephson
机构
*
Department of Chemical, Biochemical, and Environmental Engineering, University of Maryland Baltimore County(化学、生物化学与环境工程系,马里兰大学巴尔的摩县分校)
;
Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County(计算机科学与电气工程系,马里兰大学巴尔的摩县分校)