paper-with-me

Papers

BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism

2025-05-27 · Qinzhuo Wu, Pengzhi Gao, Wei Liu, Jian Luan

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 mechanisms for detecting and recovering from errors. To address these shortcomings, we propose the BacktrackAgent, a robust framework that incorporates a backtracking mechanism to improve task completion efficiency. BacktrackAgent includes verifier, judger, and reflector components as modules for error detection and recovery, while also applying judgment rewards to further enhance the agent's performance. Additionally, we develop a training dataset specifically designed for the backtracking mechanism, which considers the outcome pages after action executions. Experimental results show that BacktrackAgent has achieved performance improvements in both task success rate and step accuracy on Mobile3M and Auto-UI benchmarks. Our data and code will be released upon acceptance.

📄 PDF Abstract BibTeX arXiv:2505.20660

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Focus 설명 없음

Similar Papers 제목 키워드 기반

Enhancing Lifelong Multi-Agent Path-finding by Using Artificial Potential Fields

2025-05-28 · Arseniy Pertzovsky, Roni Stern, Ariel Felner, Roie Zivan

We explore the use of Artificial Potential Fields (APFs) to solve Multi-Agent Path Finding (MAPF) and Lifelong MAPF (LMAPF) problems. In MAPF, a team of agents must move to their goal locations without collisions, wherea…

Multi-Agent Path Finding

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

2026-03-15 · Shengda Fan, Xuyan Ye, Yupeng Huo, Zhi-Yuan Chen 외 arxiv

While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reasoning where errors are often rectifiable via backtracking, tool-use failur…

Mathematical Reasoning

Density- and elongation speed-dependent error correction in RNA polymerization

2021-03-09 · Xinzhe Zuo, Tom Chou

Backtracking of RNA polymerase (RNAP) is an important pausing mechanism during DNA transcription that is part of the error correction process that enhances transcription fidelity. We model the backtracking mechanism of R…

WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment

2025-12-14 · Mahir Labib Dihan, Tanzima Hashem, Mohammed Eunus Ali, Md Rizwan Parvez arxiv

LLM-based agents often operate in a greedy, step-by-step manner, selecting actions solely based on the current observation without considering long-term consequences or alternative paths. This lack of foresight is partic…

ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA

2025-03-10 · Zhao Xinjie, Fan Gao, Rui Yang, Yingjian Chen 외

Recent advances in large language models (LLMs) have significantly improved multi-hop question answering (QA) through direct Chain-of-Thought (CoT) reasoning. However, the irreversible nature of CoT leads to error accumu…

Multi-hop Question AnsweringQuestion AnsweringRetrieval