arXiv cs.AI· Sen Yang, Jiaduo Lin, Zehong Huang, Wen Liu·· 12 小时前AI 评分38
Reglos：具备递归自我改进能力的自进化个人记忆智能体
Reglos: A Self-Evolving Personal Memory Agent with Recursive Self-Improvement
AI 导读
Reglos 是一个免训练的个人记忆智能体，通过递归自我改进让编码智能体根据失败轨迹提出 harness 补丁，并由另一模型家族的评审器筛查是否针对 benchmark 作弊。
正文 · 原文
Abstract: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.
| Comments: | 12 pages, 7 figures, 8 tables. Website: this https URL |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.06049 [cs.AI] |
| (or arXiv:2611.06049v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06049 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sen Yang [view email]
[v1]
Wed, 4 Nov 2026 06:56:04 UTC (474 KB)
来源：arXiv cs.AI · arxiv.org