Metraipolis › archive › dc_29aed4332802

MEMIG: Self-evolving Memory Construction for Antibody Optimization — arXiv:2610.41245

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41245
License (as archived): CC0-1.0
Archived: 2026-11-02T07:18:53.919Z
SHA-256 of the archived text: 497b8dbc4408d6f12908c56c08c762f3fd16de0437b491981942feef66bf76d9
Stable URL of this page: https://metraipolis.com/documento/dc_29aed4332802

How to cite

MEMIG: Self-evolving Memory Construction for Antibody Optimization — arXiv:2610.41245 — arXiv (en), https://arxiv.org/abs/2610.41245 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_29aed4332802 (Metraipolis archive dc_29aed4332802, sha256 497b8dbc4408d6f12908c56c08c762f3fd16de0437b491981942feef66bf76d9)

BibTeX

@misc{dc29aed4332802,
  title = {MEMIG: Self-evolving Memory Construction for Antibody Optimization — arXiv:2610.41245},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41245},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_29aed4332802; sha256 497b8dbc4408d6f12908c56c08c762f3fd16de0437b491981942feef66bf76d9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41245. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

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/2610.41245 — 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 2026-11-02T07:16:57.157Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).