cs.AINov 6, 2026

Rethinking Agent Trajectory Compression: A Workflow-Aware Perspective

Authors: Qijia Zhuang, Rui Liu, Wenqi Hu, Yuxiang Ren

Organizations: Nanjing University, Nanjing, China · Northeastern University, China

Abstract

As long-horizon agents increasingly rely on multi-step tool interactions to accomplish complex tasks, their execution trajectories continuously accumulate structured outputs and intermediate artifacts, leading to growing context overhead. Existing compression methods primarily rely on text importance or fixed truncation rules, often overlooking cross-step dependencies within workflows and potentially discarding critical information required for subsequent task execution. To address this challenge, we propose WAAC, a workflow-aware framework for agent trajectory compression. WAAC structurally models successful historical trajectories to extract reusable workflow compression experience and incorporates online backward dependency analysis to dynamically identify information retention requirements. By combining current dependency constraints with historical experience, WAAC selects appropriate compression strategies for different types of historical information. Experiments on PinchBench and Odysseys demonstrate that WAAC achieves an overall score of 87.6 and a perfect completion rate of 19.0%, respectively, while reducing execution costs by 19.7% and 29.1% compared with the strongest baseline methods. These results demonstrate the effectiveness of workflow-aware trajectory compression in improving task performance and cost efficiency for long-horizon agents. Code and resources are available at https://anonymous.4open.science/r/waac-6527/.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. StateComp: Learning When to Compress History in Long Horizon Agents

    Sep 23, 2026Mingxuan Wang, Hongyue Chen, Yinglong Guo +6Context CompressionLong-Horizon LLM Agents

  2. A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression

    Apr 21, 2026Jincheng Ren, Siwei Wu, Yizhi Li +8Terminal AgentsLong-Horizon Agent Tasks

  3. Towards Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability

    Aug 6, 2026Guanghui Min, Liang Wu, Mayank Darbari +2AI Agent EvaluationLong-Horizon LLM Agents