Skip to content

Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents

Oct 2026 · 0 citations · 30 references
Computer Science

TL;DR

CarryOn is introduced, an object-oriented context runtime that organizes continuation around reusable task objects that builds a context view from continuation carriers, complementary execution context, and a live tail of recent interactions.

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

View source

Similar papers

#artificial intelligence Preprint Sep 2026

FlowState: Execution State as Memory for Long-Horizon LLM Agents

Compared with a full-context baseline using the same DeepSeek-V4-Flash model, FlowState improves the average success rate on MemoryArena and the average pass rate on $\tau^3$-Bench by 4.55 and 13.95 percentage points, respectively, while reducing total token consumption.

Ming-Hao Li, Bang-Yan Li, Zi-Fan Wang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Staying on Task: Testing the Foundations of Long-Horizon Agent Reliability

Long-horizon agentic workflows require models to sustain repeated state-dependent actions all while the context grows, sub-task complexity changes, and new data arrives. Each situation represents an independent axis along which an agent may fail. An agent reconciling a long ledger, for example, must repeatedly read its...

Jeffrey Willette, Krishna C. Puvvada, Boris Ginsburg · 0 citations
#artificial intelligence Preprint Sep 2026

ContextRender: From Execution Dependencies to Agent Context

This work develops Tool-Flow Analysis to track how later operations reuse information from earlier tool results, providing a signal called observed reuse, andlations show that observed reuse improves task performance and retention of results reused later.

Savini Kashmira, Jayanaka L. Dantanarayana, Ling-Jia Tang et al. · 0 citations
#artificial intelligence Preprint Oct 2026

MemTrace: State-Consistent Memory for Long-Horizon Coding Agents

As coding agents take on long-horizon software evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupled challenges: (1) accumulated histories strain context budgets, and (2) repository changes can invalidate earlier execution evidence. Existing approaches address these cha...

Hong-Ming Xu, Le Zhou, Zhong-He Jin et al. · 0 citations
#artificial intelligence Preprint Sep 2026

CADOC: Cache-Aware Dynamic Object Context for Long-Horizon Agents

CADOC (Cache-Aware Dynamic Object Context), an online algorithm that replaces structured objects with compact Cards while preserving exact, on-demand retrieval of their original contents, is proposed, demonstrating that efficient compression depends not only on shortening prompts but also on scheduling edits to preserv...

Jun-Jie Yao, Zhang-Chen Zhou, Zhi-qin John Xu · 0 citations
#artificial intelligence Preprint Sep 2026

StateComp: Learning When to Compress History in Long Horizon Agents

This work proposes State Conditioned Compression (StateComp), a framework that determines when historical interactions can be safely compressed according to the current agent state, and demonstrates that it reduces total agent and summarization tokens while maintaining task performance, and achieves a 12.67-fold speedu...

Ming-Xuan Wang, Hong-Yue Chen, Ying-Long Guo et al. · 1 citation

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.