翻訳待ち：Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability

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 6 Aug 2026] Title:Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability View a PDF of the paper titled Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability, by Guanghui Min and 4 other authors View PDF HTML (experimental) Abstract:Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood. In this preliminary empirical study, we show that compression can weaken the influence of recent interactions, increasing blocked actions, repeated exploration, and instability across runs. Motivated by these observations, we introduce TRACE, a verifier-guided framework that evaluates individual compaction events through paired closed-loop continuations from the same environment state and uses summary preferences to optimize a natural-language compression prompt while keeping all models frozen. Initial results on AppWorld show improvements over existing compression baselines in task performance, multi-run reliability, and context--execution efficiency. These findings provide early evidence for boundary-local evaluation as a promising direction for reliable agent context compression. Comments: 31 pages, 6 figures Subjects: Machine Learning (cs.LG) Cite as: arXiv:2608.06503 [cs.LG] (or arXiv:2608.06503v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.06503 arXiv-issued DOI via DataCite (pending registration) Submission history From: Guanghui Min [view email] [v1] Thu, 6 Aug 2026 18:42:02 UTC (262 KB) Full-text links: Access Paper: View a PDF of the paper titled Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability, by Guanghui Min and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG new | recent | 2026-08 Change to browse by: cs 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?) IArxiv recommender toggle IArxiv Recommender (What is IArxiv?) 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?)