SOURCE-LINKED INTELLIGENCE

Learning to Reason and Use Tools through Unsupervised Fine-Tuning in Task-Oriented Dialog Systems

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Current dialogue systems struggle with dynamic information retrieval, often leading to hallucinations and lower response accuracy. We address this by adapting the ReAct framework for Task-Oriented Dialogue, enabling Large Language Models (LLMs) to access external knowledge and produce factual responses. Mainly, we propose an unsupervised fine-tuning pipeline that harvests reasoning trajectories via in-context learning inference. High-quality samples are filtered using an LLM-based judge to construct a robust training set. This is enhanced by a unsupervised self-improvement loop, where improved

Read original source ↗ Open in workspace

recordType

paper

region

Global