Daniel Fleischer

Advancing AI reasoning through open-source tools and research

I’m an AI Research Engineer working to make artificial intelligence more capable and accessible. I build open-source libraries that help developers integrate AI into their workflows, focusing on the intersection of research and practical implementation.

My primary contributions include open-source tools for running AI workflows on Intel hardware and a framework that simplifies LLM fine-tuning for RAG applications. Currently developing agentic systems for enhanced reasoning and experimenting with GRPO training methods to advance AI capabilities.

Always excited to collaborate with fellow researchers and engineers pushing the boundaries of what AI can accomplish.

latest posts

Sep 07, 2025	Breaking Language Barriers in Mathematical AI: Introducing Hebrew Math Tutor
Aug 29, 2025	Jujutsu Impressions
Jun 23, 2025	Built an MCP server for LLMs to search email from terminal \| Daniel Fleischer posted on the topic \| LinkedIn
Jun 10, 2025	Summarize Hacker News Posts with Haystack & OPEA \| Haystack
Dec 01, 2024	המודל שלכם הוזה? כך תבנו בעצמכם מערכת RAG \| גיקטיים
Oct 09, 2024	Intel Labs Introduces RAG-FiT Open-Source Framework for Retrieval Augmented Generation in LLMs - Intel Community
Aug 23, 2023	Open Domain Q&A using Dense Retrievers in fastRAG \| by Daniel Fleischer \| Medium

selected publications

RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation

Daniel Fleischer, Moshe Berchansky, Moshe Wasserblat, and 1 more author

Aug 2024

Abs DOI

Implementing Retrieval-Augmented Generation (RAG) systems is inherently complex, requiring deep understanding of data, use cases, and intricate design decisions. Additionally, evaluating these systems presents significant challenges, necessitating assessment of both retrieval accuracy and generative quality through a multi-faceted approach. We introduce RAG Foundry, an open-source framework for augmenting large language models for RAG use cases. RAG Foundry integrates data creation, training, inference and evaluation into a single workflow, facilitating the creation of data-augmented datasets for training and evaluating large language models in RAG settings. This integration enables rapid prototyping and experimentation with various RAG techniques, allowing users to easily generate datasets and train RAG models using internal or specialized knowledge sources. We demonstrate the framework effectiveness by augmenting and fine-tuning Llama-3 and Phi-3 models with diverse RAG configurations, showcasing consistent improvements across three knowledge-intensive datasets. Code is released as open-source in https://github.com/IntelLabs/RAGFoundry.
SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models

Daniel Fleischer, Moshe Berchansky, Gad Markovits, and 1 more author

Feb 2025

Abs DOI

In the rapidly evolving field of Natural Language Processing, Large Language Models (LLMs) are tasked with increasingly complex reasoning challenges. Traditional methods like chain-of-thought prompting have shown promise but often fall short in fully leveraging a model’s reasoning capabilities. This paper introduces SQuARE (Sequential Question Answering Reasoning Engine), a novel prompting technique designed to improve reasoning through a self-interrogation paradigm. Building upon CoT frameworks, SQuARE prompts models to generate and resolve multiple auxiliary questions before tackling the main query, promoting a more thorough exploration of various aspects of a topic. Our expansive evaluations, conducted with Llama 3 and GPT-4o models across multiple question-answering datasets, demonstrate that SQuARE significantly surpasses traditional CoT prompts and existing rephrase-and-respond methods. By systematically decomposing queries, SQuARE advances LLM capabilities in reasoning tasks. The code is publicly available at https://github.com/IntelLabs/RAG-FiT/tree/square.