Metraipolis › archive › dc_af73a139bf7f
Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents — arXiv:2609.01272
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01272
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:32:24.504Z
- SHA-256 of the archived text
477228cbb6511419fbf40dc6aa31a883be0d7490dfaffe09c38eec2f9ba0f73c- Stable URL of this page
https://metraipolis.com/documento/dc_af73a139bf7f
How to cite
Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents — arXiv:2609.01272 — arXiv (en), https://arxiv.org/abs/2609.01272 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af73a139bf7f (Metraipolis archive dc_af73a139bf7f, sha256 477228cbb6511419fbf40dc6aa31a883be0d7490dfaffe09c38eec2f9ba0f73c)
BibTeX
@misc{dcaf73a139bf7f,
title = {Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents — arXiv:2609.01272},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01272},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af73a139bf7f; sha256 477228cbb6511419fbf40dc6aa31a883be0d7490dfaffe09c38eec2f9ba0f73c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01272. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Prospective memory means carrying out a deferred intention at the right future cue while other work continues. Benchmarks now isolate it as an agent skill, yet frontier LLMs still struggle: the best published PM-Bench scaffold reaches only 65.1% Set-F1. We argue that this loop is schema-constrained state tracking rather than open-ended reasoning, and that small models can execute it when the action space is typed. We propose the Prospective Intention Store (PIS) that puts lifecycle logic in code and scoped language work on the model. The scaffold is agentic and training-free: no selector fine-tuning and no trajectory distillation. On PM-Bench, DeepSeek-Chat with PIS reaches 82.9% Set-F1. On Gemma-E2B, Set-F1 is only 4.2% without a store and at most 6.6% under seven retrospective memories, while PIS reaches 66.2%. PIS further reaches 70.1% Set-F1, where retrospective memory methods stay at most 54.4%. PIS sets a new state of the art on this benchmark and enables small models to surpass the published large-model scaffold. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.01272 — 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 2026-10-17T06:15:12.684Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).