Metraipolis › archive › dc_3fab427fe755
Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design — arXiv:2609.22086
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22086
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T01:05:39.081Z
- SHA-256 of the archived text
1eb14fd82bb3b45ce3ef17ad709f6c630e4bdadc392545c0342f53d4bac45582- Stable URL of this page
https://metraipolis.com/documento/dc_3fab427fe755
How to cite
Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design — arXiv:2609.22086 — arXiv (en), https://arxiv.org/abs/2609.22086 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3fab427fe755 (Metraipolis archive dc_3fab427fe755, sha256 1eb14fd82bb3b45ce3ef17ad709f6c630e4bdadc392545c0342f53d4bac45582)
BibTeX
@misc{dc3fab427fe755,
title = {Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design — arXiv:2609.22086},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22086},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3fab427fe755; sha256 1eb14fd82bb3b45ce3ef17ad709f6c630e4bdadc392545c0342f53d4bac45582},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22086. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many interdependent actions, yet outcomes admit no reliable programmatic oracle. We introduce a continual adaptation framework in which a frozen frontier model operates professional design software through more than 230 tools, while an external procedural memory of natural-language skills accumulates and refines reusable design procedures from experience. The memory widens by acquiring procedures for recurring uncovered subtasks and deepens by revising existing procedures against their own successful and failed executions, while a matched replay gate admits only changes that repair failures without regressing observed successes. Five rounds over 1,406 real user briefs and 1,869 automatically graded trajectories, with no weight updates and no human labels, grow the bank from 76 documentation-derived skills to 139 and raise GenEval2 execution success on Claude-Sonnet-4 from 72.7% to 99.3% (+11.99 points in generation quality), with 61.8% and 67.6% win rates against the no-skill agent across four specialized design benchmarks on Claude-Sonnet-4 and Claude-Opus-4.6. We further show the two mechanisms are effective in combination: on 200 held-out briefs from user-traffic benchmark, widening or deepening alone reaches a 49.4% / 48.6% win rate over the no-skill agent, while their combination reaches 58.5% (p = 0.025). Procedural memory offers a practical route to continual adaptation of agents under noisy, unverifiable feedback. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.22086 — 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 2026-10-10T00:23:42.486Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).