Application of Agent Technology in Voice Assistant Scenarios
Senior algorithm engineer Qi Jianwei from Xiaomi presents a comprehensive overview of building a large‑model‑centric Agent framework for voice assistants, covering prompt design, information retrieval, RAG processes, and future optimization directions to enhance performance and stability.
Qi Jianwei, a senior algorithm engineer at Xiaomi, works on large‑scale language model training, inference, and applications within the XiaoAi voice assistant team.
He is responsible for developing deep‑learning algorithms for various voice‑assistant scenarios and has built algorithmic frameworks that improve XiaoAi's user experience. His research in semantic understanding, dialogue management, and information retrieval has been published in venues such as ACL and NAACL.
Talk Title: Application of Agent Technology in Voice Assistant Scenarios
The presentation describes how to construct an Agent framework centered on large models to address the increasingly complex and diverse requirements of voice‑assistant applications. By integrating prompt engineering, information retrieval, and Retrieval‑Augmented Generation (RAG) workflows, the proposed Agent achieves strong performance and stable behavior.
Talk outline:
Overall Agent architecture and fundamental principles
Agent applications in voice‑assistant scenarios
Future optimization directions
Audience benefits:
Understanding the basic principles of Agents
Learning about potential challenges and solutions when deploying Agents in production
Exploring feasible directions for further Agent optimization
Scan the QR code to inquire about ticket purchase.
DataFunTalk
Dedicated to sharing and discussing big data and AI technology applications, aiming to empower a million data scientists. Regularly hosts live tech talks and curates articles on big data, recommendation/search algorithms, advertising algorithms, NLP, intelligent risk control, autonomous driving, and machine learning/deep learning.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.