Loading...
MANJU: A Multi-Agent Framework for Natural Just-in-Time Understanding in Thai
Author(s)
Koseeyaumporn, Sawit
Saiprom, Siratee
Promfiy, Watin
Tarnpradab, Sansiri
Date Issued
January 1, 2026
Type
Conference Paper
Abstract
This paper presents MANJU (Multi-Agent AI for Natural Just-in-Time Understanding), an automated platform for Thai-language customer service delivered through just-in-time voice interaction. MANJU transcribes a customer's spoken query, applies multi-agent reasoning with retrieval-augmented generation (RAG) to determine the optimal response strategy, and synthesises a reply in natural Thai, delivering the first audio segment within approximately 1.8 s via sentence-level streaming. A visual drag-and-drop work flow editor enables non-technical operators to compose and modify conversation logic without programming.Evaluated on 50 standard Thai customer-service queries and 23 adversarial edge cases, MANJU achieves 100% intent routing accuracy, 62% RAG-grounded responses (GR), 78% edge-case acceptability with 100% safety, and Mean Opinion Score (MOS) = 4.33 for VoiceDesign TTS. End-to-end median latency is 6.07 s; the primary bottleneck is Qwen3-TTS at Real-Time Factor (RTF) = 1.54, partially offset by sentence-level streaming.
Citation
Proceedings 23rd International Joint Conference on Computer Science and Software Engineering Jcsse 2026, 588-593, 2026