cs.CLNov 13, 2026

CarryOn: Learning What to Keep in Context for Long-Horizon LLM Agents

Authors: Lihuan Li, Ruiyi Yang, Jiru Wang, Yifan Duan, Xiachong Lin, Hao Xue, Yang Song, Flora Salim

Organizations: University of New South Wales, Sydney, Australia · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China

Abstract

Long-horizon LLM agents can coordinate tools and applications to complete complex, multi-step tasks. As their interaction histories grow, effective context management becomes essential for reliable and efficient execution. Existing methods reduce context through summarization, pruning, or history selection. However, shorter contexts do not necessarily support better decisions: summaries can omit exact details needed for later actions, while retaining entire interactions can carry substantial irrelevant information. We propose CarryOn, a lightweight context manager that pairs compact execution state with fine-grained, source-linked evidence. A learned selector and adaptive retention policy keep relevant evidence available without additional LLM calls for context management. We introduce two complementary evaluation metrics: SαS_α prioritizes task success while accounting for resource use, and normalized cost per success (NCS) measures the resources spent per successful task. Across AppWorld, OfficeBench, and Tau2 Telecom with three LLM Actors, CarryOn achieves 75.7% macro-averaged task success, exceeding the strongest baseline by 6.7 percentage points. It also achieves the best average scores on both metrics.

Figures & tables

Appendix figures & tables24 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Learning Agent-Compatible Context Management for Long-Horizon Tasks

    May 29, 2026Lu Yi, Runlin Lei, Liuyi Yao +6Long-Horizon Agent TasksLLM Context Management

  2. ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

    Aug 28, 2026Zhuoshi Pan, Qizhi Pei, Junru Lu +4LLM Context ManagementLong-Horizon LLM Agents