← Search

Qinzhuo Wu

7 accepted papers

2025

BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism

EMNLP 2025

Graphical User Interface (GUI) agents have gained substantial attention due to their impressive capabilities to complete tasks through multiple interactions within GUI environments. However, existing agents primarily focus on enhancing the accuracy of individual actions and often lack effective mech

Cited by 0SourcePDFScholar
2025

ReachAgent: Enhancing Mobile Agent via Page Reaching and Operation

NAACL 2025long

Recently, mobile AI agents have gained increasing attention. Given a task, mobile AI agents can interact with mobile devices in multiple steps and finally form a GUI flow that solves the task. However, existing agents tend to focus on most task-relevant elements at each step, leading to local optima…

2025

SPO: Self Preference Optimization with Self Regularization

EMNLP 2025

Direct Preference Optimization (DPO) is a widely used offline preference optimization algorithm that enhances the simplicity and training stability of reinforcement learning through reward function reparameterization from PPO. Recently, SimPO (Simple Preference Optimization) and CPO (Contrastive Pre

Cited by 0SourcePDFScholar
2024

MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding

EMNLP 2024finding

Recently, mobile AI agents based on VLMs have been gaining increasing attention. These works typically utilize VLM as a foundation, fine-tuning it with instruction-based mobile datasets. However, these VLMs are typically pre-trained on general-domain data, which often results in a lack of fundamenta…

2024

ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback

EMNLP 2024main

Recently, tool-augmented LLMs have gained increasing attention. Given an instruction, tool-augmented LLMs can interact with various external tools in multiple rounds and provide a final answer. However, previous LLMs were trained on overly detailed instructions, which included API names or parameter…

2021

An Edge-Enhanced Hierarchical Graph-to-Tree Network for Math Word Problem Solving

EMNLP 2021finding

Math word problem solving has attracted considerable research interest in recent years. Previous works have shown the effectiveness of utilizing graph neural networks to capture the relationships in the problem. However, these works did not carefully take the edge label information and the long-rang…