---
id: 20261117-T0-06
title: "CarryOn：让长周期LLM Agent学会\"该留什么上下文\""
title_en: "CarryOn: Teaching Long-Horizon LLM Agents What to Keep in Context"
url: https://ai.daily.yangsir.net/daily/20261117-T0-06
issue_date: 2026-11-17
publish_date: 2026-11-16T05:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2611.17808
---

# CarryOn：让长周期LLM Agent学会"该留什么上下文"

新论文CarryOn针对长周期LLM Agent的上下文管理问题提出方案。这类Agent需要协调工具和应用完成多步任务，交互历史不断增长，现有方法通常压缩或截断上下文，但容易丢掉后续步骤所需的关键信息。CarryOn的核心是学习在上下文中保留什么，而非简单压缩。对需要运行长时间任务的Agent系统而言，这类方法直接影响执行可靠性和token成本。

## English Version

**CarryOn: Teaching Long-Horizon LLM Agents What to Keep in Context**

A new paper, CarryOn, tackles context management for long-horizon LLM agents that coordinate tools and applications across multi-step tasks. As interaction histories grow, existing methods typically compress or truncate context, which can discard information later steps depend on. CarryOn instead learns what to keep in context rather than simply shrinking it. For agent systems running extended tasks, this bears directly on execution reliability and token cost.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2611.17808)

**详情页**：https://ai.daily.yangsir.net/daily/20261117-T0-06

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*