cs.AINov 4, 2026

From Handcrafted to Generative: RLVR-Optimized Icon Generation for Alexa+

Authors: Rohan Sequeira, Matthew Rosenberg, Amin Mahmoudabadbozchelou, Oleg Poliannikov, Jonathan Rubin

Organizations: University of Southern California · Amazon Alexa

Abstract

Alexa+ devices with screens display animated icons during conversations to visually reinforce what is being said. The original set of these icons was hand-drawn by designers one at a time, a process that produces polished results but is time-consuming and cannot scale to the range of topics encountered in open-ended conversation. We describe an automated pipeline, deployed in production, that generates these vectorised animated icons from a text description alone and surfaces relevant animations to customers based on their ongoing conversation. The pipeline decomposes icon creation into a sequence of stages (image generation, semantic decomposition, vectorisation, styling, and animation). Its quality is determined at the very first of these, image generation, on which every downstream stage depends. We therefore focus on improving this first and most critical stage. Because the icons are rendered on small display canvases under strict design guidelines, generations are often unsuitable for production. Supervised fine-tuning is not viable, as no dataset of line-art icons exists under these constraints. Instead, we design objective verifiers that automatically flag generations violating the design guidelines, and use them to fine-tune a flow matching image generation model via reinforcement learning from verifiable rewards (RLVR). The fine-tuned model raises the pass rate from 15.7% to 58.7% (3.7x) under a VLM judge that is independent of the reward model. Both the trained model and the verifier are deployed in the production pipeline, where the verifier also serves as the automated quality gate before final design review.

Figures & tables

Explore similar work

CardsList
  1. RULER: Instance-aware Rubric Rewards for SVG Generation

    Sep 21, 2026Hangyu Ran, Yuhao Zheng, Yingying Zhang +2Text-to-SVG GenerationVector Graphics Generation

  2. RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time

    Apr 13, 2026Haozhe Wang, Cong Wei, Weiming Ren +3Reward ModelingMultimodal Reward Modeling

  3. Reinforcement Learning from Intermediate Renders for Image-to-Code Generation

    Sep 28, 2026Omri Kaduri, Kate Feingold, Phillip Isola +1RL for Code GenerationImage-to-Code Generation