paper-with-me

Papers

EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-Exploration

2025-12-22 · Runze Li, Yuwen Zhai, Bo Xu, LiWu Xu, Nian Shi, Wei Zhang, Ran Lin, Liang Wang arxiv

Contemporary GUI agents, while increasingly capable due to advances in Large Vision-Language Models (VLMs), often operate with a critical limitation: they treat each task in isolation, lacking a mechanism to systematically learn from past successes. This digital ''amnesia'' results in sub-optimal performance, repeated errors, and poor generalization to novel challenges. To bridge this gap, we introduce EchoTrail-GUI, a novel framework designed to mimic human-like experiential learning by equipping agents with a dynamic, accessible memory. Our framework operates in three distinct stages. First, during Experience Exploration, an agent autonomously interacts with GUI environments to build a curated database of successful task trajectories, validated by a reward model. Crucially, the entire knowledge base construction is thus fully automated, requiring no human supervision. Second, in the Memory Injection stage, upon receiving a new task, our system efficiently retrieves the most relevant past trajectories to serve as actionable ''memories''. Finally, during GUI Task Inference, these memories are injected as in-context guidance to inform the agent's reasoning and decision-making process. We demonstrate the efficacy of our approach on benchmarks including Android World and AndroidLab. The results show that EchoTrail-GUI significantly improves the task success rate and operational efficiency of baseline agents, validating the power of structured memory in creating more robust and intelligent GUI automation.

📄 PDF Abstract BibTeX arXiv:2512.19396

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents

2026-02-04 · Xiaohui Zhang, Zequn Sun, Chengyuan Yang, Yaqin Jin 외 arxiv

Memory management is essential for LLM agents in long-term interactions. Current memory frameworks typically treat agents as passive ``recorders'' and retrieve information without understanding its deeper implications. T…

Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead

2026-03-09 · Zhongming Yu, Naicheng Yu, Hejia Zhang, Wentao Ni 외 arxiv

As LLM agents evolve into collaborative multi-agent systems, their memory requirements grow rapidly in complexity. This position paper frames multi-agent memory as a computer architecture problem. We distinguish shared a…

Experience Transfer for Multimodal LLM Agents in Minecraft Game

2026-04-07 · Chenghao Li, Jun Liu, Songbo Zhang, Huadong Jian 외 arxiv

Multimodal LLM agents operating in complex game environments must continually reuse past experience to solve new tasks efficiently. In this work, we propose Echo, a transfer-oriented memory framework that enables agents …

M$^2$: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrieval

2026-02-28 · Dawei Yan, Haokui Zhang, Guangda Huzhang, Yang Li 외 arxiv

Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical bottleneck. Prevailing strategies often r…

S2SServiceBench: A Multimodal Benchmark for Last-Mile S2S Climate Services

2026-02-15 · Chenyue Li, Wen Deng, Zhuotao Sun, Mengxi Jin 외 arxiv

Subseasonal-to-seasonal (S2S) forecasts play an essential role in providing a decision-critical weeks-to-months planning window for climate resilience and sustainability, yet a growing bottleneck is the last-mile gap: tr…