Metraipolis › archive › dc_9fbb7a407c64
The Sleeping Agent: What Gist-Based Context Compression Loses and Why — arXiv:2608.11775
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11775
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:15:29.725Z
- SHA-256 of the archived text
7000a2b7d002420177977802c50b5e4e404bb239b5ef9a9bf4c707ebe1c613be- Stable URL of this page
https://metraipolis.com/documento/dc_9fbb7a407c64
How to cite
The Sleeping Agent: What Gist-Based Context Compression Loses and Why — arXiv:2608.11775 — arXiv (en), https://arxiv.org/abs/2608.11775 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9fbb7a407c64 (Metraipolis archive dc_9fbb7a407c64, sha256 7000a2b7d002420177977802c50b5e4e404bb239b5ef9a9bf4c707ebe1c613be)
BibTeX
@misc{dc9fbb7a407c64,
title = {The Sleeping Agent: What Gist-Based Context Compression Loses and Why — arXiv:2608.11775},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11775},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9fbb7a407c64; sha256 7000a2b7d002420177977802c50b5e4e404bb239b5ef9a9bf4c707ebe1c613be},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11775. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood. We use Salience-Weighted Consolidation (SWC), a biologically-inspired compression framework motivated by sleep-based memory consolidation, as a diagnostic probe to study when gist compression helps and when it hurts. SWC scores conversation history by salience, partitions it into priority tiers, and applies structured gist abstraction to mid-priority content. Evaluating four conditions on all ten LoCoMo conversations---1,935 matched text-only questions in total, 1,501 used in the primary aggregate after excluding Category 5 (adversarial) questions---at temperature 0, we find a consistent task-type interaction: gist compression substantially outperforms truncation on multi-hop reasoning and single-hop factual questions, but temporal questions remain substantially harder under compression, with compressed conditions scoring well below the full-context reference on the conversations where both are evaluated. We trace this failure to a specific mechanism: the gist abstraction prompt preserves relational and event structure while discarding dates and times. A preservation analysis across all ten conversations confirms the mechanism: an approximately 20-fold increase in temporal expression preservation (3.05% to 62.39%) with a one-sentence prompt modification, while named entity and event preservation rates barely change (x1.02 and x1.11), demonstrating that the fix is a precision instrument. The prompt modification recovers +0.314 [0.254, 0.375] judge accuracy on category-2 (temporal) questions in the matched set. Code and results: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.11775 — 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 2026-10-19T05:08:46.644Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).