We develop KnowThyself, an agentic assistant that advances large language model (LLM) interpretability. Existing tools provide useful insights but remain fragmented and code-intensive. KnowThyself consolidates these capabilities into a chat-based interface, where users can upload models, pose natural language questions, and obtain interactive visualizations with guided explanations. At its core, an orchestrator LLM first reformulates user queries, an agent router further directs them to specialized modules, and the outputs are finally contextualized into coherent explanations. This design lowers technical barriers and provides an extensible platform for LLM inspection. By embedding the whole process into a conversational workflow, KnowThyself offers a robust foundation for accessible LLM interpretability.
@article{arxiv.2511.03878,
title = {KnowThyself: An Agentic Assistant for LLM Interpretability},
author = {Suraj Prasai and Mengnan Du and Ying Zhang and Fan Yang},
journal= {arXiv preprint arXiv:2511.03878},
year = {2025}
}
Comments
5 pages, 1 figure, Accepted for publication at the Demonstration Track of the 40th AAAI Conference on Artificial Intelligence (AAAI 26)