CarryOn 论文提出面向对象的上下文运行时，提升长程智能体效率
Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents
长程智能体老是背着全部历史跑，token 爆炸。这篇 CarryOn 换个思路存任务对象，OSWorld 上省了一半 token 还更准，做 agent 的可以看看。
论文提出 CarryOn，一个面向对象的上下文运行时，用可复用的任务对象替代完整交互历史来组织长程智能体的上下文。它在折叠时跨轮维护 carrier 记录，只修订受影响的记录，未受影响的记录直接延续。在 OSWorld 2.0 和 BrowseComp-Plus 两个基准上，性能分别提升 5.8% 和 7.0%，总 token 用量分别降低 51.9% 和 22.9%。
Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents
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
