Metraipolis › archive › dc_00c472a7dbd3
Interpreting at Write Time: A Policy Ablation for Multi-Goal Agent Memory — arXiv:2610.02897
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02897
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:49:20.545Z
- SHA-256 of the archived text
97db301157a115f767ff7d9557cf78075a8f3ea4de032e9fe4d79afbfabec999- Stable URL of this page
https://metraipolis.com/documento/dc_00c472a7dbd3
How to cite
Interpreting at Write Time: A Policy Ablation for Multi-Goal Agent Memory — arXiv:2610.02897 — arXiv, https://arxiv.org/abs/2610.02897 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_00c472a7dbd3 (Metraipolis archive dc_00c472a7dbd3, sha256 97db301157a115f767ff7d9557cf78075a8f3ea4de032e9fe4d79afbfabec999)
BibTeX
@misc{dc00c472a7dbd3,
title = {Interpreting at Write Time: A Policy Ablation for Multi-Goal Agent Memory — arXiv:2610.02897},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02897},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_00c472a7dbd3; sha256 97db301157a115f767ff7d9557cf78075a8f3ea4de032e9fe4d79afbfabec999},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02897. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A long-running assistant cannot keep everything it has seen, so it summarises. Summarising is not neutral: what is kept is chosen against some notion of what the record is for, and that choice is made once, before anyone knows which of the user's standing goals will ask. Goals rarely disagree about what happened. They disagree about which parts of it were worth the space. Once the history is too long to re-read, the summary replaces the stream, and whatever it left out is gone. We ask what a memory should summarise for when it serves several standing goals at once. Three policies answer differently: summarise with no goal in view, write one summary covering every goal, or write one summary per goal and read them together. We compare them across several models and event streams, holding the read step fixed so that only the write differs. The goals do pull apart: summaries written for different goals overlap each other less than a summary overlaps a rewrite of itself. Per-goal summaries win on relevance, completeness and accuracy, and the all-goal summary loses even to the neutral one written at a fraction of its budget. Interpreting at write pays off, but only for the goal that later asks. 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/2610.02897 — 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 2026-10-05T22:45:55.647Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).