AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。
[Submitted on 14 Oct 2026] Title:ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation View a PDF of the paper titled ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation, by Tengda Guo (1) and 11 other authors View PDF HTML (experimental) 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 substantial gains in task performance and memory fidelity. Without retaining historical screenshots at deployment, ECHOES achieves competitive performance with a favorable performance-inference-cost trade-off and exhibits positive zero-shot transfer to unseen visual planning tasks. Comments: 22 pages, 7 figures, 13 tables Subjects: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2610.22408 [cs.AI] (or arXiv:2610.22408v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2610.22408 arXiv-issued DOI via DataCite (pending registration) Submission history From: Tengda Guo [view email] [v1] Wed, 14 Oct 2026 14:39:41 UTC (3,286 KB) Full-text links: Access Paper: View a PDF of the paper titled ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation, by Tengda Guo (1) and 11 other authors View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.AI new | recent | 2026-10 Change to browse by: cs cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)