Improve Reasoning LLM models' reasoning capabilities with tools

Témavezető:	Virág Fausztin Asztrik
	Lain Consulting Kft.
email:	fuszti@gmail.com

Projekt leírás

"The MCP Solver bridges Large Language Models (LLMs) with symbolic solvers through the Model Context Protocol (MCP), an open-source standard for AI system integration. Providing LLMs access to formal solving and reasoning capabilities addresses their key deficiency while leveraging their strengths. Our implementation offers interfaces for constraint programming (Minizinc), propositional satisfiability (PySAT), and SAT modulo Theories (Python Z3). The system employs an editing approach with iterated validation to ensure model consistency during modifications and enable structured refinement." - abstract of a recent paper.

The goal of this project is to find datasets, like math or algorithmic problems, where we can improve LLM reasoning with proper tools, like the mentioned MCP servers.

If you have any other ideas, like using integer program solvers as tools with LLMs, then you can apply for this project too, because there are many other opportunities in different fields.

Előfeltételek

Python programming. Basic level knowledge of formal logical systems. Basic level knowledge of LLMs or neural networks.

Hivatkozások

https://arxiv.org/abs/2501.00539v2