Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA
Yiran Zhang, Mingyang Lin, Mark Dras, Usman Naseem
Abstract
Recent research has increasingly focused on the reasoning capabilities of Large Language Models (LLMs) in multi-turn interactions, as these scenarios more closely mirror real-world problem-solving. However, analyzing the intricate reasoning processes within these interactions presents a significant challenge due to complex contextual dependencies and a lack of specialized visualization tools, leading to a high cognitive load for researchers. To address this gap, we present VISTA, an web-based Visual Interactive System for Textual Analytics in multi-turn reasoning tasks. VISTA allows users to visualize the influence of context on model decisions and interactively modify conversation histories to conduct "what-if" analyses across different models. Furthermore, the platform can automatically parse a session and generate a reasoning dependency tree, offering a transparent view of the model
BibTeX
@inproceedings{aaai2026_beyondtheblackbo,
title = {Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA},
author = {Yiran Zhang and Mingyang Lin and Mark Dras and Usman Naseem},
booktitle = {AAAI 2026},
year = {2026}
}