Metraipolis › archive › dc_bc2e60f67989

HyMem: Hierarchical Context Management for Long-Horizon Agents via Information Isolation — arXiv:2608.15703

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15703
License (as archived)
CC0-1.0
Archived
2026-10-18T17:26:10.484Z
SHA-256 of the archived text
7da86a986eee1278d118ec4ca250fc9caa34f5a9aeed7147f37c7ec99141bf75
Stable URL of this page
https://metraipolis.com/documento/dc_bc2e60f67989

How to cite

HyMem: Hierarchical Context Management for Long-Horizon Agents via Information Isolation — arXiv:2608.15703 — arXiv (en), https://arxiv.org/abs/2608.15703 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc2e60f67989 (Metraipolis archive dc_bc2e60f67989, sha256 7da86a986eee1278d118ec4ca250fc9caa34f5a9aeed7147f37c7ec99141bf75)
BibTeX
@misc{dcbc2e60f67989,
  title = {HyMem: Hierarchical Context Management for Long-Horizon Agents via Information Isolation — arXiv:2608.15703},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15703},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc2e60f67989; sha256 7da86a986eee1278d118ec4ca250fc9caa34f5a9aeed7147f37c7ec99141bf75},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15703. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) agents often perform poorly on complex, long-horizon tasks because their context becomes increasingly cluttered over time. As interactions accumulate, detailed execution traces and intermediate outputs dominate the context, making it difficult for the model to retain and use high-level planning information. Most existing methods address this issue through compression or retrieval applied to a single, flat context, which does not clearly separate different types of context information and often leads to degraded reasoning. To address this challenge, we propose HyMem, a hierarchical framework that explicitly separates the agent's context into distinct functional layers. HyMem organizes context by function to separate high-level planning from execution and complex analysis. Its isolated reasoning module handles complex subtasks without adding intermediate reasoning traces to the persistent planning context, while its memory management module preserves task progress across context refreshes through structured summaries. These components reduce redundant context accumulation, retain task-critical information, and support coherent long-horizon reasoning within a limited context window. Experiments on GAIA and Browsecomp-plus show that, with DeepSeek-V4, HyMem achieves average Pass@1 scores of 66.7% and 61.3%, outperforming the strongest baseline by 6.1 and 4.7 percentage points, respectively. Further analysis indicates that HyMem effectively controls the growth of the reasoning context, allowing the model to maintain focus and accuracy across complex, long-horizon tasks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15703 — 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 2026-10-18T16:29:13.824Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).