collaborators

7 papers

cs.AI2026

UP-NRPA: User Portrait based Nested Rollout Policy Adaptation for Planning with Large Language Models in Goal-oriented Dialogue Systems

Hui Wang, Fafa Zhang, Meng Liu +2

To address the challenge that current dialogue policy planning methods struggle to dynamically adapt to diverse user characteristics, this paper proposes a User Portrait based Nest…

cs.AI2025

CogMCTS: A Novel Cognitive-Guided Monte Carlo Tree Search Framework for Iterative Heuristic Evolution with Large Language Models

Hui Wang, Yang Liu, Xiaoyu Zhang +1

Automatic Heuristic Design (AHD) is an effective framework for solving complex optimization problems. The development of large language models (LLMs) enables the automated generati…

cs.CL2025

A General Highly Accurate Online Planning Method Integrating Large Language Models into Nested Rollout Policy Adaptation for Dialogue Tasks

Hui Wang, Fafa Zhang, Xiaoyu Zhang +1

In goal-oriented dialogue tasks, the main challenge is to steer the interaction towards a given goal within a limited number of turns. Existing approaches either rely on elaborate…

cs.CL2025

MMWOZ: Building Multimodal Agent for Task-oriented Dialogue

Pu-Hai Yang, Heyan Huang, Heng-Da Xu +3

Task-oriented dialogue systems have garnered significant attention due to their conversational ability to accomplish goals, such as booking airline tickets for users. Traditionally…

cs.AI2025

Planning of Heuristics: Strategic Planning on Large Language Models with Monte Carlo Tree Search for Automating Heuristic Optimization

Hui Wang, Xufeng Zhang, Chaoxu Mu

Heuristics have achieved great success in solving combinatorial optimization problems~(COPs). However, heuristics designed by humans require too much domain knowledge and testing t…

cs.AI2025

One for All: A General Framework of LLMs-based Multi-Criteria Decision Making on Human Expert Level

Hui Wang, Fafa Zhang, Chaoxu Mu

Multi-Criteria Decision Making~(MCDM) is widely applied in various fields, using quantitative and qualitative analyses of multiple levels and attributes to support decision makers…