Jul 2026 · COLM 2026 Workshop on Agent Behavior · Paper accepted

SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents has been accepted to the COLM 2026 Workshop on Agent Behavior. SimGym grounds browser agents in real traffic to forecast how storefront changes affect buyer behavior, shortening experimentation from weeks to under an hour without exposing real shoppers to untested variants.

Jul 2026 · COLM 2026 Learning from Situated Interaction Workshop · Paper accepted

SimPersona: Learning Discrete Buyer Personas from Raw Clickstreams for Grounded E-Commerce Agents has been accepted to the COLM 2026 Workshop on Learning from Situated and Embodied Interaction. SimPersona learns compact buyer types directly from clickstreams, giving web agents grounded and diverse behavior while preserving each merchant's real buyer distribution.

Jul 2026 · Shopify Engineering · New blog

New engineering blog: Teaching Sidekick to say no: automated data curation with LLM judge consensus. We share how consensus across LLM judges turns noisy production interactions into reliable training data, helping a domain-specific Sidekick model recognize impossible requests and refuse them well instead of producing an ungrounded answer.

Jun 2026 · arXiv preprint

New preprint: EARS: Explanatory Abstention for Reliable Sub-Agent Modeling in Large-scale Multi-Agent Systems. We treat sub-agent abstention as an inter-agent communication protocol — instead of over-answering ambiguous or unsupported requests, a sub-agent exposes an actionable failure state to the coordinator for clarification, rerouting, or fallback. On a large-scale e-commerce assistant, EARS raises the response pass rate from 68.5% to 78.9%.

Jun 2026 · NeurIPS 2026 · Workshop proposal

I'm on the organizing committee — together with collaborators from top universities and frontier industry labs — proposing the NeurIPS 2026 Workshop on User and Environment Simulation. We're actively recruiting Program Committee members from diverse backgrounds. If you're interested, please reach out.

May 2026 · ICML 2026 RLxF Workshop · Paper accepted

Our paper, ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents, has been accepted to the ICML 2026 RLxF Workshop, with open-source code released.

Teaching Sidekick to say no: automated data curation with LLM judge consensus

Using consensus across LLM judges to curate training data at scale and teach domain-specific models when—and how—to refuse impossible requests.

Flow generation through natural language: an agentic modeling approach

Bringing agentic modeling from idea to production, with the lessons learned along the way.

2,000 robots walk into a shop...

An engineering deep dive into how SimGym was built, scaled, and applied to simulate e-commerce agent behavior, with a focus on inference optimization.

Shopify

Agentic Foundation Modeling

Sidekick — Shopify's AI-powered commerce assistant, helping merchants run and grow their businesses through natural-language guidance and agentic actions.

SimGym — a framework for user behavior simulation in e-commerce with traffic-grounded VLM agents, enabling realistic experimentation before launch.

Coverage: Sidekick 2025 · Sidekick 2026 · SimGym

Amazon · Stores Foundational AI

Foundation Modeling and Inference Optimization

Rufus — Amazon's generative AI–powered conversational shopping assistant, helping customers research products, compare options, and decide what to buy in natural language.

Coverage: Rufus Science · Rufus Product · Rufus Multi Modal

Amazon · Alexa

Recommendation

Alexa Brain — recommendation and personalization behind Amazon Alexa, powering skill discovery and proactive suggestions across hundreds of millions of devices.

Coverage: Amazon Alexa Developer Blog