Metraipolis › archive › dc_2d723a523ebb
Adapting the Process of Adaptation: Darwinian, Lamarckian, and Agent-Directed Evolution in AI — arXiv:2611.07048
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07048
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:41:32.395Z
- SHA-256 of the archived text
85a26581b8ad5492f17317fde708f70c5cdf81a96cc815f01ccc9acffa287bc5- Stable URL of this page
https://metraipolis.com/documento/dc_2d723a523ebb
How to cite
Adapting the Process of Adaptation: Darwinian, Lamarckian, and Agent-Directed Evolution in AI — arXiv:2611.07048 — arXiv (en), https://arxiv.org/abs/2611.07048 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2d723a523ebb (Metraipolis archive dc_2d723a523ebb, sha256 85a26581b8ad5492f17317fde708f70c5cdf81a96cc815f01ccc9acffa287bc5)
BibTeX
@misc{dc2d723a523ebb,
title = {Adapting the Process of Adaptation: Darwinian, Lamarckian, and Agent-Directed Evolution in AI — arXiv:2611.07048},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07048},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2d723a523ebb; sha256 85a26581b8ad5492f17317fde708f70c5cdf81a96cc815f01ccc9acffa287bc5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07048. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Evolution has shaped intelligence for billions of years. Artificial intelligence (AI) now raises a striking possibility: intelligence may begin to direct its own evolution. As AI agents become capable of modifying and evaluating their own behavior, how quickly could they improve, and how can that improvement remain safe? We develop a theoretical framework comparing Darwinian, Lamarckian, and agent-directed evolution following environmental change. Darwinian evolution relies on natural selection, Lamarckian evolution adds inherited learning, and agent-directed evolution allows agents to generate and evaluate behavioral variants and choose how extensively to search. When learning is sufficiently effective, these mechanisms exhibit progressively faster adaptation. Generating more variants accelerates adaptation, while optimal search effort depends on learning ability, problem difficulty, and experimentation costs. However, an agent's ability to direct its improvement does not ensure that improvements are evaluated against the intended objective. When the evaluation target is misspecified, additional search accelerates convergence toward the wrong behavior, even as measured performance improves. In recursive self-improvement, such errors may persist across generations, posing challenges for AI safety. Independent evaluation and oversight must keep pace with autonomous AI development. The central challenge is not simply to accelerate the evolution of intelligence, but to preserve humanity's ability to guide its direction, limit its speed, and intervene when necessary. 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/2611.07048 — 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 2026-11-06T14:18:42.635Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).