Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design
Designer-RSI grows design-agent procedural memory from user traffic, raising Claude Sonnet 4 GenEval2 success to 99.3%.
Designer-RSI keeps a frozen frontier model operating professional design software through more than 230 tools while an external procedural memory of natural-language skills accumulates from experience. Five rounds over 1,406 real user briefs and 1,869 graded trajectories, with no weight updates or human labels, grow the skill bank from 76 to 139. GenEval2 execution success on Claude Sonnet 4 rises from 72.7% to 99.3%, with win rates of 61.8% and 67.6% against a no-skill agent on Claude Sonnet 4 and Claude Opus 4.6. Combining skill widening and deepening reaches a 58.5% win rate on 200 held-out briefs.
- Frozen model uses over 230 design tools; memory stores natural-language skills.
- Five rounds grow the skill bank from 76 to 139 without weight updates.
- Claude Sonnet 4 GenEval2 success rises from 72.7% to 99.3%.
- Widening plus deepening beats either mechanism alone on 200 held-out briefs.
- Vendors
- Anthropic
- Organizations
- Anthropic
- AI models
- Claude Sonnet 4Claude Opus 4.6
From the original article
1 min read at arxiv.orgProfessional 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.
By Hongyang Du · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.