Metraipolis › archive › dc_4cd3d00874c6
Reglos: A Self-Evolving Personal Memory Agent with Recursive Self-Improvement — arXiv:2611.06049
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06049
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:16:53.601Z
- SHA-256 of the archived text
c50f0ee7eb4d1410e8aef9509393ca28077d1583158daf5028efea779077e7ac- Stable URL of this page
https://metraipolis.com/documento/dc_4cd3d00874c6
How to cite
Reglos: A Self-Evolving Personal Memory Agent with Recursive Self-Improvement — arXiv:2611.06049 — arXiv (en), https://arxiv.org/abs/2611.06049 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4cd3d00874c6 (Metraipolis archive dc_4cd3d00874c6, sha256 c50f0ee7eb4d1410e8aef9509393ca28077d1583158daf5028efea779077e7ac)
BibTeX
@misc{dc4cd3d00874c6,
title = {Reglos: A Self-Evolving Personal Memory Agent with Recursive Self-Improvement — arXiv:2611.06049},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06049},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4cd3d00874c6; sha256 c50f0ee7eb4d1410e8aef9509393ca28077d1583158daf5028efea779077e7ac},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06049. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Personal agents draw on past conversations to tailor their responses to each user. Their memory systems store and update what each user says, and coding agents now also rewrite the harness that turns this memory into the model's context. Such patches risk overfitting, because one tested only on the failures it targets can fix those cases and help nowhere else. We present Reglos, a training-free personal memory agent that tests whether harness changes help beyond the failures they were written to fix. Its self-evolving memory adds to each user's append-only record with every conversation, as new preferences supersede old ones and facts can be forgotten. Its harness improves through recursive self-improvement, in which a coding agent proposes patches from failure traces and a critic from a second model family screens each one for benchmark gaming. After the harness is frozen, a fixed evaluator decides which further patches to accept. With the same backbone behind every system, Reglos outperforms state-of-the-art memory systems such as Mem0, MemOS and EverOS, reaching 61.3% and 84.0% on PersonaMem-v2 and LongMemEval-S with Qwen3.8-27B, and 57.5% and 87.2% with GPT-5.6 Luna. 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/2611.06049 — 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 2026-11-05T18:12:49.004Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).