ResearchTrend.AI
  • Papers
  • Communities
  • Organizations
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.02158
22
0

Reflection-Based Memory For Web navigation Agents

2 June 2025
Ruhana Azam
Aditya Vempaty
A. Jagmohan
ArXiv (abs)PDFHTML
Main:4 Pages
10 Figures
Bibliography:2 Pages
3 Tables
Appendix:6 Pages
Abstract

Web navigation agents have made significant progress, yet current systems operate with no memory of past experiences -- leading to repeated mistakes and an inability to learn from previous interactions. We introduce Reflection-Augment Planning (ReAP), a web navigation system to leverage both successful and failed past experiences using self-reflections. Our method improves baseline results by 11 points overall and 29 points on previously failed tasks. These findings demonstrate that reflections can transfer to different web navigation tasks.

View on arXiv
Comments on this paper