9 papers
Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection
Petmongkon Pornpichitsuwan, Krittin Pachtrachai, Touchapon Kraisingkorn
Voice agents built on large language models (LLMs) now handle customer calls, but in regulated applications completing the task is not enough: the agent must follow a conversationa…
Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format
Touchapon Kraisingkorn, Krittin Pachtrachai, Wachiravit Modecrua
Language models fine-tuned on customer behavior can predict outcomes and generate explanations, but these readouts are often treated as interchangeable. Holding model checkpoint an…
Large Behavior Model: A Promptable Digital Twin of the Retail Customer
Wachiravit Modecrua, Krittin Pachtrachai, Touchapon Kraisingkorn
Customer behavior modeling underpins recommendation, marketing, and decision support, yet existing approaches either optimize predictive accuracy without explaining decisions or si…
InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost
Krittanon Kaewtawee, Petmongkon Pornpichitsuwan, Natchaya Temyingyong +4
Matching influencers (KOLs) to free-form, multi-part Thai marketing criteria is today served either by keyword search over structured profiles, which misses semantic fit, or by pro…
Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration
Wachiravit Modecrua, Krittanon Kaewtawee, Krittin Pachtrachai +1
Training tool-calling agents with reinforcement learning on multi-turn tasks remains challenging due to sparse outcome rewards and difficult credit assignment across conversation t…
From Transcripts to AI Agents: Knowledge Extraction, RAG Integration, and Robust Evaluation of Conversational AI Assistants
Krittin Pachtrachai, Petmongkon Pornpichitsuwan, Wachiravit Modecrua +1
Building reliable conversational AI assistants for customer-facing industries remains challenging due to noisy conversational data, fragmented knowledge, and the requirement for ac…
ROAD: Reflective Optimization via Automated Debugging for Zero-Shot Agent Alignment
Natchaya Temyingyong, Daman Jain, Neeraj Kumarsahu +6
Automatic Prompt Optimization (APO) has emerged as a critical technique for enhancing Large Language Model (LLM) performance, yet current state-of-the-art methods typically rely on…
Cloning a Conversational Voice AI Agent from Call\,Recording Datasets for Telesales
Krittanon Kaewtawee, Wachiravit Modecrua, Krittin Pachtrachai +1
Recent advances in language and speech modelling have made it possible to build autonomous voice assistants that understand and generate human dialogue in real time. These systems…
Online estimation of the hand-eye transformation from surgical scenes
Krittin Pachtrachai, Francisco Vasconcelos, Danail Stoyanov
Hand-eye calibration algorithms are mature and provide accurate transformation estimations for an effective camera-robot link but rely on a sufficiently wide range of calibration d…