Metraipolis › archive › dc_f7941bf6808b
Memorizing Who, Knowing How: Benchmarking Personal and Procedural Memory for Persistent Assistants — arXiv:2610.20022
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20022
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:02:17.855Z
- SHA-256 of the archived text
a5021a4c4c17d8d49b9769d88645f2ae1429da1aa0974c3c848f476ffada8985- Stable URL of this page
https://metraipolis.com/documento/dc_f7941bf6808b
How to cite
Memorizing Who, Knowing How: Benchmarking Personal and Procedural Memory for Persistent Assistants — arXiv:2610.20022 — arXiv (en), https://arxiv.org/abs/2610.20022 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f7941bf6808b (Metraipolis archive dc_f7941bf6808b, sha256 a5021a4c4c17d8d49b9769d88645f2ae1429da1aa0974c3c848f476ffada8985)
BibTeX
@misc{dcf7941bf6808b,
title = {Memorizing Who, Knowing How: Benchmarking Personal and Procedural Memory for Persistent Assistants — arXiv:2610.20022},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20022},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f7941bf6808b; sha256 a5021a4c4c17d8d49b9769d88645f2ae1429da1aa0974c3c848f476ffada8985},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20022. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Memory systems for persistent personal agents must move beyond isolated memories, maintaining both personal memory about whom they serve and procedural memory about how to act. Crucially, in harness-based personal assistance, procedures or skills are inherently user-conditioned: personal context determines which procedures apply, how they are instantiated, and when they should change. Existing benchmarks typically emphasize either personal or procedural memory, leaving their interaction underexplored. We introduce PraxisMemBench, a harness-based benchmark for persistent personal assistance across daily-life and work trajectories, where personal and procedural memory evolve together and later tasks depend on both. Experiments show that maintaining two memory types separately is insufficient, with completion dropping from single-type to interdependent dependencies (84.6% to 77.9%). More broadly, across existing methods, relation-related failures increase from early to late sessions as interaction history grows (59.8% to 72.9%), revealing a continual-maintenance challenge: writing correct memories is not enough if their evolving content and organization cannot be preserved for later retrieval. To address this, we propose PraxisMem, which uses privileged joint-state supervision to internalize the ability to maintain memory content and organization into the memory manager, with location-aware GRPO and dynamic residual-routed OPSD. PraxisMem reaches 40.78% overall Session Success Rate, compared with 20.60% for Claude Code's native memory. 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/2610.20022 — 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 2026-10-15T19:35:48.285Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).