mlsanityData to 14 Oct 2026

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

arXiv 2610.18784 ↗First posted 13 Oct 2026cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 30 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

23 of 30 references.

References · 23

  1. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  2. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  3. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agentscited by 238
  4. 2025BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agentcited by 200
  5. 2025Memory OS of AI Agentcited by 150
  6. 2025Scaling Long-Horizon LLM Agent via Context-Foldingcited by 148
  7. 2025ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarizationcited by 141
  8. 2025ACON: Optimizing Context Compression for Long-horizon LLM Agentscited by 136
  9. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Modelcited by 106
  10. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Managementcited by 103
  11. 2025Reducing Cost of LLM Agents with Trajectory Reductioncited by 48
  12. 2025Context as a Tool: Context Management for Long-Horizon SWE-Agentscited by 43
11 more
  1. 2026OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Taskscited by 40
  2. 2026Learning Agent-Compatible Context Management for Long-Horizon Taskscited by 15
  3. 2026LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Taskscited by 13
  4. 2025AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Managementcited by 11
  5. 2026Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agentscited by 11
  6. 2026InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agentscited by 10
  7. 2026Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoningcited by 7
  8. 2026StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structurecited by 7
  9. 2026FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agentscited by 6
  10. 2026Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agentscited by 6
  11. 2026Context as an Environment: Programmatic Context Management for Long-Horizon Agentscited by 4

Built on by

Not cited yet.