Metraipolis › archive › dc_7b6bb213719c
DarwinX: Evolving Agent Harnesses Through Natural Selection — arXiv:2608.07545
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.07545
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:01:04.892Z
- SHA-256 of the archived text
22c762c256dcf5504935ff1ddfda2a9ce1c6fe5f6221e14eed51fd6a31151f1a- Stable URL of this page
https://metraipolis.com/documento/dc_7b6bb213719c
How to cite
DarwinX: Evolving Agent Harnesses Through Natural Selection — arXiv:2608.07545 — arXiv (en), https://arxiv.org/abs/2608.07545 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b6bb213719c (Metraipolis archive dc_7b6bb213719c, sha256 22c762c256dcf5504935ff1ddfda2a9ce1c6fe5f6221e14eed51fd6a31151f1a)
BibTeX
@misc{dc7b6bb213719c,
title = {DarwinX: Evolving Agent Harnesses Through Natural Selection — arXiv:2608.07545},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.07545},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b6bb213719c; sha256 22c762c256dcf5504935ff1ddfda2a9ce1c6fe5f6221e14eed51fd6a31151f1a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07545. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow. Self-improvement loops already edit harnesses, yet single-lineage search is path-dependent and local wins often regress other tasks. We introduce DarwinX, which treats self-evolution as selection over a population of harnesses with the model frozen: a preserve-and-extend contract admits only variants that extend coverage without regressing, an archive keeps alternative lineages for recombination, and failure-, teacher-, and self-derived evidence share one edit interface. Fitness comes from each benchmark's own verifier: no gold solutions, no hand-picked winners. Across four benchmarks that progressively separate the evolution signal from the test, one loop adds about 17 points on average: Terminal-Bench 2.1 rises +7.7 to 83.2% on a matched base and to the verified frontier at 84.7% on a stronger one; TerminalWorld's held-out split reaches 68.3%, ahead of every off-the-shelf agent; WebArena-Infinity real-task pass@1 rises from 43.5% to 93.0% audit-clean; and a Terminal-Bench 2.1 harness transfers unchanged to SWE-bench Verified. What evolves is general agent competence, not benchmark-specific patches, so it survives changes of task, verifier, and base model. A frozen model need not be a fixed agent: harness selection turns evaluation compute into durable capability. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-11 in cs.SE). Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.07545 — 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 2026-10-19T09:00:31.506Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).