Skip to content
aiqbench takeAI Products

aiqbench analysis

Ottilie addresses a critical gap in generative AI by moving beyond generic chatbots to create a specialized virtual host capable of real-time sales conversion and emotional intelligence. By grounding responses in verified knowledge bases and adapting discourse strategies dynamically, the system significantly improves factual accuracy and viewer engagement compared to standard LLMs. Its successful deployment on commodity hardware demonstrates that highly specific, socially intelligent agents can operate autonomously without extensive retraining for new markets.
Source coveringarXiv
What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Ottilie: A Socially Intelligent Virtual Host for Sales-Driven Live Commerce

arXiv2 min read

arXiv:2605.14542v2 Announce Type: replace Abstract: A skilled live-commerce host is not merely a narrator, but a sales agent who converts viewer curiosity into purchase intent through expert product knowledge, emotionally intelligent response tactics, and entertainment that serves as a vehicle for product exposure. Yet no existing AI system replicates this. Conversational recommenders treat recommendation as a terminal act, while general-purpose LLMs hallucinate product claims and default to generic promotional templates that fail to engage or persuade. We present Ottilie, a sales-conversion-oriented virtual host for Chinese beauty live commerce that grounds product responses in a verified knowledge base, adapts discourse strategy to viewer intent through empathetic amplification, evidence-backed rebuttal, and humor-mediated deflection, and supervises all four output fields simultaneously within a structured generation framework. Experiments demonstrate gains of 14% on informativeness and 5% on factual correctness, with consistent advantages in tactfulness and viewer engagement. Ottilie has been deployed as an autonomous English-language host on Twitch, where the same fine-tuned model runs unattended on a single commodity GPU and promotes the company's own product; we report how the system adapted to a new language, market, and product without retraining, and what the deployment revealed about latency and adversarial chat.

Abstract:A skilled live-commerce host is not merely a narrator, but a sales agent who converts viewer curiosity into purchase intent through expert product knowledge, emotionally intelligent response tactics, and entertainment that serves as a vehicle for product exposure. Yet no existing AI system replicates this. Conversational recommenders treat recommendation as a terminal act, while general-purpose LLMs hallucinate product claims and default to generic promotional templates that fail to engage or persuade. We present Ottilie, a sales-conversion-oriented virtual host for Chinese beauty live commerce that grounds product responses in a verified knowledge base, adapts discourse strategy to viewer intent through empathetic amplification, evidence-backed rebuttal, and humor-mediated deflection, and supervises all four output fields simultaneously within a structured generation framework. Experiments demonstrate gains of 14% on informativeness and 5% on factual correctness, with consistent advantages in tactfulness and viewer engagement. Ottilie has been deployed as an autonomous English-language host on Twitch, where the same fine-tuned model runs unattended on a single commodity GPU and promotes the company's own product; we report how the system adapted to a new language, market, and product without retraining, and what the deployment revealed about latency and adversarial chat.

10 pages, 7 figures. An earlier version, titled "VerbalValue: A Socially Intelligent Virtual Host for Sales-Driven Live Commerce", was accepted to the CVPR 2026 HiGen Workshop (non-archival). This version extends it with a deployment study

Artificial Intelligence (cs.AI)

arXiv:2605.14542 [cs.AI]

(or arXiv:2605.14542v2 [cs.AI] for this version)

Full text under the publisher's open licence · 238 words

Related coverage