ACM UIST 2026

TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking

Yuexin Sun1, Zhaohui Wang1,*, Ruiyang Liu2,†
Demian Kong2, Qian He2, Gaofeng He2, Huamin Wang2
1 Donghua University 2 Style3D Research
* Corresponding author † Project leader
Paper Supplementary
Overview of TailorCoPilot
Overview of TailorCoPilot for novice garment pattern making. Given a novice's natural-language design intent, TailorCoPilot retrieves a compatible base pattern from a pattern library and uses a vision-language model (VLM) to reason based on embedded expert knowledge from textbooks and operation traces. It then proposes stepwise editable pattern operations (e.g., SpreadPanel(), ExtendPoint()) that progressively transform the base pattern into the final garment pattern, with synchronized updates in the 3D drape.

Abstract

Experience-driven manufacturing, such as garment pattern making, faces a severe generational skills gap because its core expertise relies on undocumented tacit knowledge forged through day-to-day practice. To address this challenge, we present TailorCoPilot, an agentic pattern-making system built upon a specially designed version-control backend TailorTrace. TailorTrace models sewing patterns as structured, discrete states and records their transformations during the pattern-making process as explicit operation sequences defined upon the geometry primitives in the sewing pattern (panels, edges, vertices, and stitches). Integrated into a conventional pattern-making GUI, TailorTrace enables seamless documentation of senior experts' tacit pattern-making knowledge without breaking their daily workflow. The documented knowledge further offers interactive, pedagogical scaffolding for novices, while providing a robust foundation to power TailorCoPilot and train future generative AI models. In a user study with novices and advanced novices, TailorCoPilot improved task completion rates, reduced time and perceived workload, and yielded higher-quality artifacts compared to skill-appropriate baselines. Ultimately, TailorCoPilot demonstrates a viable pathway to capture practice-based expertise, operationalizing it to support both generative AI advancements and human apprenticeship.

Video Demonstration

Method Overview

TailorTrace overview
Overview of TailorTrace. Experts begin by exploring and modifying garment designs through an interactive frontend. As they edit, the backend captures their semantic operations as traces and maintains each design state using a unified representation that includes required 2D pattern geometry, optional 3D draping results, and multimodal metadata.
Novice walkthrough of TailorCoPilot - 8-stage workflow
Novice walkthrough of TailorCoPilot. The workflow proceeds through eight stages: (1) Design Input, (2) Pattern Initialization, (3) Garment Comparison, (4) Neuro-Symbolic Reasoning, (5) Symbolic Execution, (6) 3D Validation, (7) User Intervention, and (8) Final Output — from text/image intent to the final revised garment pattern and draped result.

Evaluation Results

Evaluation comparison - final garment results
Representative qualitative result from the user study on the complex dress task. Target image vs. baseline vs. TailorCoPilot. Baseline = participant-chosen skill-appropriate tools (AI-assisted and CAD baselines used in the user study). The baseline exhibited asymmetry, jagged edges, incorrect sleeve shape and incorrect skirt length, while TailorCoPilot better preserved the target V-neck, waist pleats and symmetry, producing a result that was structurally closer to the reference.
Application Results - final garment results
Application Results: Additional final garments generated with TailorCoPilot across diverse design prompts, demonstrating generalization beyond the user-study tasks.

BibTeX

@inproceedings{sun2026tailorcopilot,
  title     = {TailorCoPilot: Enabling Agentic Pattern Making with Version-Controlled State Tracking},
  author    = {Sun, Yuexin and Wang, Zhaohui and Liu, Ruiyang and Kong, Demian and He, Qian and He, Gaofeng and Wang, Huamin},
  booktitle = {Proceedings of the 39th Annual ACM Symposium on User Interface Software and Technology},
  series    = {UIST '26},
  year      = {2026},
  location  = {Detroit, MI, USA},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  doi       = {10.1145/3830398.3830502},
  isbn      = {979-8-4007-2856-3/2026/11}
}