paper-with-me

홈 › Papers

Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA

2025-11-13 · Yiran Zhang, Mingyang Lin, Mark Dras, Usman Naseem arxiv

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's step-by-step logical path. By providing a unified and interactive framework, VISTA significantly reduces the complexity of analyzing reasoning chains, thereby facilitating a deeper understanding of the capabilities and limitations of current LLMs. The platform is open-source and supports easy integration of custom benchmarks and local models.

📄 PDF Abstract BibTeX arXiv:2511.10182

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

2026-06-01 · Rui Yang, Qianhui Wu, Yuxi Chen, Hao Bai 외 arxiv

Building capable visual web agents requires long-horizon reasoning, precise grounding, and robust interaction with dynamic real-world websites. Despite rapid progress, the strongest systems remain largely proprietary, wh…

Reinforcement Learning

The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective

2025-06-04 · Jiin Kim, Byeongjun Shin, Jinha Chung, Minsoo Rhu

Large-language-model (LLM)-based AI agents have recently showcased impressive versatility by employing dynamic reasoning, an adaptive, multi-step process that coordinates with external tools. This shift from static, sing…

AI AgentLarge Language Model

No Black Box Anymore: Demystifying Clinical Predictive Modeling with Temporal-Feature Cross Attention Mechanism

2025-03-25 · Yubo Li, Xinyu Yao, Rema Padman

Despite the outstanding performance of deep learning models in clinical prediction tasks, explainability remains a significant challenge. Inspired by transformer architectures, we introduce the Temporal-Feature Cross Att…

Deep LearningFeature Importance

Demystifying KAN for Vision Tasks: The RepKAN Approach

2026-03-06 · Minjong Cheon arxiv

Remote sensing image classification is essential for Earth observation, yet standard CNNs and Transformers often function as uninterpretable black-boxes. We propose RepKAN, a novel architecture that integrates the struct…

Remote Sensing Image Classification

Matryoshka: Learning to Drive Black-Box LLMs with LLMs

2024-10-28 · Changhao Li, Yuchen Zhuang, Rushi Qiang, Haotian Sun 외

Despite the impressive generative abilities of black-box large language models (LLMs), their inherent opacity hinders further advancements in capabilities such as reasoning, planning, and personalization. Existing works …

In-Context Learning