Skip to content

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

Aug 2026 · 0 citations · 21 references
Computer Science

TL;DR

An unsupervised fine-tuning pipeline that harvests reasoning trajectories via in-context learning inference via in-context learning inference is proposed, enabling Large Language Models (LLMs) to access external knowledge and produce factual responses.

Abstract

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 checkpoints generate increasingly better trajectories for subsequent fine-tuning iterations. Experiments on the SIMMC dataset demonstrate that ReAct-based systems outperform baselines due to superior reasoning and tool use. Notably, our fine-tuned 8B model surpasses a 70B in-context system. Finally, we present an error analysis, impact of scene complexity, and cross-domain generalization.

View source

Similar papers

Preprint Sep 2026

HaPRL: Human-Anchored Process Reinforcement Learning for Visual Search Agent

Multi-turn visual search agents answer questions about high-resolution images by iteratively deciding where to look. Reinforcement learning for these agents rewards only the final answer, leaving the search process unsupervised. Consequently, faulty routes in which the reasoning process is erroneous yet the final resul...

Zhangquan Chen, Yao-Xin Niu, Xiang An et al. · 0 citations

Parameters vs. Context: TRACE Fine-Tuning for Robust Retrieval-Augmented Generation

Experiments across multiple knowledge-conflict scenarios and datasets show that TRACE improves robustness against misleading retrieved knowledge and reduces incomplete answers, and jointly enhance knowledge-source selection, conflict robustness, and answer quality in RAG models.

Zheng-Chen Huang, Yun-Dong Sun, Min-Rui Song et al. · 0 citations
#artificial intelligence Preprint Aug 2026

ReToolSQL: Agentic Reinforcement Learning for Robust Text-to-SQL

ReToolSQL is presented, a two-stage training framework for text-to-SQL that combines a supervised warm-start on rejection-sampled reasoning traces with agentic reinforcement fine-tuning (RFT) over multi-turn tool-use trajectories and shows that a properly designed SFT$\to-RFT pipeline over tool-use trajectories is a pr...

Pratik Kakkar, Chandra Dhir, Ravi Shankar et al. · 0 citations
Open access 2026

Enhancing Auditory Reasoning in Large Audio–Language Models Via Supervised Fine-Tuning and Reinforcement Learning With Verifiable Rewards

It is suggested that auditory reasoning can benefit from training strategies tailored to audio signals and objective answer verification, and they provide empirical evidence for applying RLVR to large audio–language models.

Jian Wang, Sheng-Yan Hao · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.