Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design
Du, Yan, Flores and Kadav (Adobe and Brown University) keep a frontier model frozen while it operates professional design software through more than 230 tools, and let an external procedural memory of natural-language skills grow and improve from real user traffic.
Ask this paper
Widen and deepen. Memory widens by adding procedures for recurring uncovered subtasks and deepens by revising existing procedures against their own successful and failed runs.
Replay gate. A matched replay gate accepts a memory change only if it repairs failures without breaking previously successful cases.
Results. Five rounds over 1,406 user briefs and 1,869 auto-graded trajectories grow the bank from 76 to 139 skills and raise GenEval2 execution success on Claude-Sonnet-4 from 72.7% to 99.3%, with no weight updates or human labels.
Combination matters. On 200 held-out briefs widening alone reaches a 49.4% win rate over the no-skill agent, deepening alone 48.6%, and both together 58.5% (p = 0.025).
Abstract
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.