Towards Automated Functional Equation Proving: A Benchmark Dataset and A Domain-Specific In-Context Agent

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Buali, Mahdi, Hoehndorf, Robert
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911963488976896
author Buali, Mahdi
Hoehndorf, Robert
author_facet Buali, Mahdi
Hoehndorf, Robert
contents Automated Theorem Proving (ATP) faces challenges due to its complexity and computational demands. Recent work has explored using Large Language Models (LLMs) for ATP action selection, but these methods can be resource-intensive. This study introduces FEAS, an agent that enhances the COPRA in-context learning framework within Lean. FEAS refines prompt generation, response parsing, and incorporates domain-specific heuristics for functional equations. It introduces FunEq, a curated dataset of functional equation problems with varying difficulty. FEAS outperforms baselines on FunEq, particularly with the integration of domain-specific heuristics. The results demonstrate FEAS's effectiveness in generating and formalizing high-level proof strategies into Lean proofs, showcasing the potential of tailored approaches for specific ATP challenges.
format Preprint
id arxiv_https___arxiv_org_abs_2407_14521
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Automated Functional Equation Proving: A Benchmark Dataset and A Domain-Specific In-Context Agent
Buali, Mahdi
Hoehndorf, Robert
Artificial Intelligence
Computation and Language
Symbolic Computation
Automated Theorem Proving (ATP) faces challenges due to its complexity and computational demands. Recent work has explored using Large Language Models (LLMs) for ATP action selection, but these methods can be resource-intensive. This study introduces FEAS, an agent that enhances the COPRA in-context learning framework within Lean. FEAS refines prompt generation, response parsing, and incorporates domain-specific heuristics for functional equations. It introduces FunEq, a curated dataset of functional equation problems with varying difficulty. FEAS outperforms baselines on FunEq, particularly with the integration of domain-specific heuristics. The results demonstrate FEAS's effectiveness in generating and formalizing high-level proof strategies into Lean proofs, showcasing the potential of tailored approaches for specific ATP challenges.
title Towards Automated Functional Equation Proving: A Benchmark Dataset and A Domain-Specific In-Context Agent
topic Artificial Intelligence
Computation and Language
Symbolic Computation
url https://arxiv.org/abs/2407.14521