返回首页
arXiv AI··论文与技术

ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation

中文摘要

回声(ECHOES)通过历史压缩与蒸馏,优化长视界GUI代理的视觉信息利用,降低成本,增强可靠性。

English Summary

ECHOES enhances long-horizon GUI agents by compressing visual history with privileged training data, reducing costs and improving reliability.

原文节选

arXiv:2610.22408v1 Announce Type: new Abstract: Long-horizon GUI agents rely on visual history to maintain task states, but retaining historical screenshots increases visual-token usage and inference costs, while textual summaries can discard critical state information, undermining long-horizon reliability. We propose ECHOES, which leverages training-time privileged information to guide textual history compression and strengthen long-horizon reasoning. Specifically, ECHOES adopts a Compression-Think-Action (CTA) format to recursively update a textual history state and reason. The same model, given privileged multi-image inputs, serves as a teacher that provides dense token-level on-policy distillation on student-generated CTA rollouts. Our Perception-Memory Fidelity (PMF) Gap-guided OPD-RL framework dynamically balances privileged distillation and task-reward optimization, with periodic teacher updates supporting continued improvement. We further introduce ECHOESBMK, a fine-grained diagnostic benchmark derived from real GUI agent failure trajectories to jointly evaluate visual perception and cross-modal state retention. Experiments on four GUI benchmarks and ECHOESBMK demonstrate s…