Metraipolis › archive › dc_80fffeabbde0

StateComp: Learning When to Compress History in Long Horizon Agents — arXiv:2609.27298

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.27298
License (as archived): CC0-1.0
Archived: 2026-10-08T09:11:18.007Z
SHA-256 of the archived text: d3a0aba1947edc794947d24942f2ce6e55787bba3851de4ff8b5bd80962a5119
Stable URL of this page: https://metraipolis.com/documento/dc_80fffeabbde0

How to cite

StateComp: Learning When to Compress History in Long Horizon Agents — arXiv:2609.27298 — arXiv (en), https://arxiv.org/abs/2609.27298 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_80fffeabbde0 (Metraipolis archive dc_80fffeabbde0, sha256 d3a0aba1947edc794947d24942f2ce6e55787bba3851de4ff8b5bd80962a5119)

BibTeX

@misc{dc80fffeabbde0,
  title = {StateComp: Learning When to Compress History in Long Horizon Agents — arXiv:2609.27298},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27298},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_80fffeabbde0; sha256 d3a0aba1947edc794947d24942f2ce6e55787bba3851de4ff8b5bd80962a5119},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27298. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-horizon agents continuously accumulate interaction history during task execution, yet the importance of past interactions changes as the agent state evolves. Existing context management methods largely compress history based on fixed windows, periodic schedules, or current relevance, overlooking a more fundamental question: when has a past interaction become safe to replace? Premature compression may remove information still needed for future actions, while overly conservative retention leads to substantial context overhead. To address this, we propose State Conditioned Compression (StateComp), a framework that determines when historical interactions can be safely compressed according to the current agent state. StateComp constructs KEEP and READY supervision through a two-stage annotation procedure and trains an imbalance-aware router on hidden representations from a frozen language model. A bounded state representation further reduces the cost of evaluating long histories, while adjacent READY interactions are grouped into continuous spans and replaced with compact summaries during execution. Experiments on WorkBuddyBench show that StateComp reduces total agent and summarization tokens by 52.27% while maintaining task performance, and achieves a 12.67-fold speedup in representation extraction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.27298 — 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 2026-10-08T08:13:26.496Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).