Metraipolis › archive › dc_a28cc781a301
MutMem: Cryptographically Authorized Mutation in Persistent Agent Memory — arXiv:2608.02843
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.02843
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:18:15.486Z
- SHA-256 of the archived text
611b3933ced9aa65adf2ad45f39d57f3dd7e5af2f754fcb33c154c4c7d12ebe7- Stable URL of this page
https://metraipolis.com/documento/dc_a28cc781a301
How to cite
MutMem: Cryptographically Authorized Mutation in Persistent Agent Memory — arXiv:2608.02843 — arXiv (en), https://arxiv.org/abs/2608.02843 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a28cc781a301 (Metraipolis archive dc_a28cc781a301, sha256 611b3933ced9aa65adf2ad45f39d57f3dd7e5af2f754fcb33c154c4c7d12ebe7)
BibTeX
@misc{dca28cc781a301,
title = {MutMem: Cryptographically Authorized Mutation in Persistent Agent Memory — arXiv:2608.02843},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.02843},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a28cc781a301; sha256 611b3933ced9aa65adf2ad45f39d57f3dd7e5af2f754fcb33c154c4c7d12ebe7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02843. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Persistent agent memory must adapt as later outcomes change earlier evidence, yet mutable retrieval weights create an attribution problem: reviewers must distinguish authorized adaptation from database tampering. We present MutMem, an authorized-mutation protocol in HOM-AIMOS, a persistent agent-memory engine. MutMem retains memory content, records signed positive and negative outcome evidence without age-based expiry, and commits each nontrivial weight change as a housekeeper-authorized transition. Each transition binds a terminal provenance node, signer epoch, quantized old and new weights, a no-fork predecessor, and two domain-separated SHA-256 commitments. Ed25519 verification runs in both the database writer and a portable verifier. Content classified as poison-likely is retained with signed, revisable labels used by recall as trust evidence. We evaluate utility, mutation integrity, and poisoning adaptation. HOM-AIMOS answers 459/500 LongMemEval questions correctly under LLM judgment (91.8%). On LoCoMo, it obtains 74.12% judged accuracy and, under a separate upstream-compatible protocol, 58.20 token F1. A native suite passes all declared authorization, topology, tamper, signer-epoch, and post-mutation-recall cases; median signed-transition latency is 4.865 ms. In a declared N=100 PoisonedRAG adaptation, no injected poison appears in attacked top-5 disclosures (0/100; 95% Wilson upper bound 3.70%), while induced target-answer attack success among 98 clean-negative targets is 1/98 (1.02%). A preregistered four-arm ablation attributes the retrieval reduction to signed stored labels: the retriever selects poison for 94/100 targets when epistemic policy is bypassed and 0/100 when labels are restored. MutMem provides evidence of integrity, authorization, traceability, and historical continuity; it does not establish content truth. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.02843 — 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 2026-10-31T12:05:52.961Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).