CarryOn：为长程智能体构建面向对象的上下文

View PDF HTML (experimental)

Abstract: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: this https URL

Comments:	24 pages. Project page: this https URL
Subjects:	Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as:	arXiv:2610.18784 [cs.AI]
	(or arXiv:2610.18784v2 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2610.18784 arXiv-issued DOI via DataCite

Submission history

From: Yuchen Lu [view email]
[v1] Tue, 13 Oct 2026 17:35:27 UTC (510 KB)
[v2] Wed, 14 Oct 2026 04:46:42 UTC (510 KB)