arXiv cs.AI· Yunhui Jang, Zach Wang, Jai Doshi, Kangway Chuang, Sidney Lisanza, Taylor Joren·· 1 天前AI 评分26
MEMIG：面向抗体优化的自进化记忆构建框架
MEMIG: Self-evolving Memory Construction for Antibody Optimization
AI 导读
MEMIG 提出一种面向生物分子优化的智能体记忆构建框架，将经验表示为可索引、定量、结构化的形式，而非自由文本重写。该框架为每条洞见分配领域标识符并累积性质 oracle 测得的定量效应，使更新局部化、检索变为精确查找，同时连接联合施加的干预并分解评估集以度量其上位效应。在计算机抗体优化任务中，MEMIG 在多数设置下提升了性能。
正文 · 原文
Abstract:Memory has become central to self-evolving LLM agents, which store and retrieve experience from past rollouts to guide future decisions. Existing systems represent this experience as free-form natural language and maintain it by rewriting, which fits tasks whose experience is narratable. However, in scientific discovery and optimization, experience is often a quantity measured by an oracle under a specific context. Rewriting it as text leaves no index for where a record should be, replaces a measurement with a description, and cannot express how interventions interact. To address this, we argue that agent memory for biomolecule optimization should instead be indexable, quantitative, and structured, and we introduce MEMIG. This memory construction framework realizes these three properties. In detail, MEMIG addresses each insight with a domain-grounded identifier and accumulates the quantitative effect measured by a property oracle, so that updates remain local and retrieval becomes an exact lookup. Next, MEMIG connects insights whose interventions are applied together and measures their epistasis by decomposing each evaluated set. Our results show that MEMIG improves performance in most settings across in silico antibody optimization tasks.
| Comments: | 10 pages |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.41245 [cs.AI] |
| (or arXiv:2610.41245v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41245 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yunhui Jang [view email]
[v1]
Fri, 30 Oct 2026 04:39:18 UTC (505 KB)
来源：arXiv cs.AI · arxiv.org