Metraipolis › archive › dc_fd35a8f01716
Memorix: Managing Memory Selections for AI Agents — arXiv:2611.00060
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00060
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:54:46.751Z
- SHA-256 of the archived text
4c08c34a68615f98e9d9c2020214384a4c4713e187a0158374385cfae22b5a31- Stable URL of this page
https://metraipolis.com/documento/dc_fd35a8f01716
How to cite
Memorix: Managing Memory Selections for AI Agents — arXiv:2611.00060 — arXiv (en), https://arxiv.org/abs/2611.00060 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd35a8f01716 (Metraipolis archive dc_fd35a8f01716, sha256 4c08c34a68615f98e9d9c2020214384a4c4713e187a0158374385cfae22b5a31)
BibTeX
@misc{dcfd35a8f01716,
title = {Memorix: Managing Memory Selections for AI Agents — arXiv:2611.00060},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00060},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd35a8f01716; sha256 4c08c34a68615f98e9d9c2020214384a4c4713e187a0158374385cfae22b5a31},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00060. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI agents now handle a growing share of tasks across sessions within a persistent project. Their behavior depends not only on the model, but heavily on the persistent state they read from the environment. Existing systems assemble this memory at use time, splicing selected files into the prompt as a one-off payload. As a result, per-task assembly is costly and can still miss critical material, failures cannot be traced or replayed, and agents can read documentation written for the wrong version. Our key insight is that what an agent should read is mostly determined by its project, so the selection can be computed once, ahead of time, and reused across tasks. We propose Memorix, an agent memory system that realizes this insight. Memorix achieves this via three key mechanisms: (1) an immutable and versioned Store pins every source by identity and reproduces historical layouts cheaply, (2) a View that splits selection (Derivations) from composition (Environment), making the result reproducible and shareable, and (3) Quests and Profiles keep a delivered view refreshable and available inside the project as sources evolve. We implement Memorix and evaluate it on SWE-ContextBench and LibEvolutionEval against mainstream agent memory systems. Precomputed Environments raise resolved rate by up to 1.5X and deliver the correct library version on every version-conditioned task, while cutting amortized cost by up to 100X and build time by up to 38X. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Operating Systems (cs.OS) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.00060 — 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 2026-11-03T10:49:38.449Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).