Papers
arxiv:2610.18784

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

Published on Oct 13
ยท Submitted by
YUCHEN LU
on Oct 19
Authors:
,

Abstract

CarryOn organizes long-horizon agent context around reusable task objects rather than interaction histories, improving efficiency and performance on complex benchmarks.

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

Community

Paper author Paper submitter

Long-horizon agents often keep revisiting how work was done, even when the results are already preserved in files and task state.

We introduce CarryOn, an object-oriented context runtime that enables agents to continue from reusable task progress rather than repeatedly compressing interaction histories.

On OSWorld 2.0 and BrowseComp-Plus, CarryOn improves performance by 5.8 and 7.0 percentage points, while reducing total token usage by 51.9% and 22.9%, respectively.

Project: https://ethannju.github.io/carryon/

This is an automated message from the ResearchStudio team.

We created an interactive ResearchStudio Reel for this paper. It includes a visual poster, a video, and a blog, all available for download in editable formats.

Visual poster for this paper

Open the ResearchStudio Reel โ†’

Download all files from Hugging Face

Please give this comment a thumbs up if you find the Reel helpful!

Want to explore or create Reels for more papers? Visit the ResearchStudio demo.

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2610.18784
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.18784 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.18784 in a dataset README.md to link it from this page.

Spaces citing this paper 1

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.