AI 译本 · Equalang
新上架PDF · 2026年11月翻译
加载中…
加载中…
arXiv · 2026
轻装上阵：为长周期智能体构建面向对象的上下文
Yuchen Lu, Julian McAuley, Lei Zhang
Long-horizon agents accumulate progress in persistent task state, yet repeatedly process interaction histories describing how that progress was achieved. This raises a natural question: can long-horizon context instead be organized around reusable progress rather than the history that produced it? In this paper, we introduce CarryOn, an object-oriented context runtime that organizes continuation around reusable task objects. Rather than treating compressed histories or reconstructed accounts of progress as the primary basis for continuation, CarryOn builds a context view from continuation carriers, complementary execution context, and a live tail of recent interactions. A core challenge is keeping this reusable basis valid after its surrounding history is retired: how can CarryOn update the basis without reconstructing the full representation at every fold? CarryOn maintains carrier records across folds, revising affected records against bound evidence and applicable environment checks while carrying forward unaffected records and jointly updating execution context. Experiments on OSWorld 2.0 and BrowseComp-Plus show improved gains of 5.8% and 7.0% while reducing total token usage by 51.9% and 22.9%, respectively. Project page: https://ethannju.github.io/carryon
长周期智能体在持久化任务状态中累积进展，却反复处理描述该进展如何达成的交互历史。这引出一个自然的问题：长周期上下文能否围绕可复用的进展来组织，而非围绕产生该进展的历史来组织？本文提出 CarryOn，一种面向对象的上下文运行时，围绕可复用的任务对象来组织延续。CarryOn 不以压缩历史或重建的进展叙述作为延续的主要依据，而是从延续载体、补充执行上下文以及近期交互的实时尾部构建上下文视图。核心挑战在于：在其周围历史被退役后，如何保持这一可复用基础的有效性——CarryOn 如何在每次折叠时不重建完整表示而更新该基础？CarryOn 跨折叠维护载体记录，依据绑定证据和适用的环境检查修订受影响的记录，同时沿用未受影响的记录并联合更新执行上下文。在 OSWorld 2.0 和 BrowseComp-Plus 上的实验分别取得 5.8% 和 7.0% 的提升，同时总 token 使用量分别减少 51.9% 和 22.9%。项目页面：https://ethannju.github.io/carryon
PDF · 2026年11月翻译