mlsanityData to 14 Oct 2026

Reflection-Based Memory For Web navigation Agents

arXiv 2506.02158 ↗First posted 2 Jun 2025cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 14 of its 23 references that are in the map. First posted on arXiv 2 Jun 2025.

Builds on

14 of 23 references.

References · 14

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  4. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
  5. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  6. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  7. 2024Autonomous Evaluation and Refinement of Digital Agentscited by 137
  8. 2024AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agentscited by 114
  9. 2024AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agentscited by 74
  10. 2023SteP: Stacked LLM Policies for Web Actionscited by 66
  11. 2024NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wildcited by 59
  12. 2024ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Datacited by 39
2 more
  1. 2024WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agentscited by 22
  2. 2024Multimodal Auto Validation For Self-Refinement in Web Agentscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 170
  2. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  3. 2026Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoningcited by 49
  4. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 19
  5. 2026When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigationcited by 14