Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents
Yuchen Lu, Julian McAuley, Lei Zhang
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: https://ethannju.github.io/carryon
Create a lesson
Related papers
AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards
Xin Gao, Yifan Yang, Xin Li et al.
MFG: Multi-turn Feedback Guided Molecular Optimization
Trieu Nguyen, Frazier N. Baker, Ruoxi Gao et al.
Who Improves the Robot? Toward Physical Recursive Self-Improvement
Hai Zhou, Fan Yang, Zeyi Chen et al.
Read the Room Before Your Model Generates
Muyao Kong, Zhihao Lin
Self-Evolving Agent Harness
Chuyang Wei, Haoxiang Guan, Minghang Zhu et al.
BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems
Xiaoguang Guo, Yaohao Long, Chuxu Zhang