Metraipolis › archive › dc_81be9bc3fcd5

Rethinking Agent Trajectory Compression: A Workflow-Aware Perspective — arXiv:2611.08865

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08865
License (as archived)
CC0-1.0
Archived
2026-11-09T22:33:47.826Z
SHA-256 of the archived text
6f6443da1a11d1672d31596056550a9a4dc49fd0074524a575ca3ca82b70a7e6
Stable URL of this page
https://metraipolis.com/documento/dc_81be9bc3fcd5

How to cite

Rethinking Agent Trajectory Compression: A Workflow-Aware Perspective — arXiv:2611.08865 — arXiv (en), https://arxiv.org/abs/2611.08865 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_81be9bc3fcd5 (Metraipolis archive dc_81be9bc3fcd5, sha256 6f6443da1a11d1672d31596056550a9a4dc49fd0074524a575ca3ca82b70a7e6)
BibTeX
@misc{dc81be9bc3fcd5,
  title = {Rethinking Agent Trajectory Compression: A Workflow-Aware Perspective — arXiv:2611.08865},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08865},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_81be9bc3fcd5; sha256 6f6443da1a11d1672d31596056550a9a4dc49fd0074524a575ca3ca82b70a7e6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08865. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.08865 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-09T22:30:47.258Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).