Request invite
Design & media · 2 November 2026
Research

Adobe Research and UC San Diego test EditAgent AI image-editing agent

Adobe Research and UC San Diego built EditAgent, an AI system that selects specialized Photoshop tools and uses a language model to pick the best result; it requires about ten times the compute, professionals preferred parallel variants in 78.5% of comparisons, and the agent needed half as many evaluation passes.

Benchmarks are the company's own; not independently verified.

Why it matters

Benchmark your image-editing roadmap against Adobe's EditAgent parallel-variant approach; users will expect faster results with fewer evaluation passes.

For product managers

For your product
What does this mean for your product?
Try it on your product
Read at The Decoder
More from this issueAll AI news from 2 Nov →
OpenAI merges Chat and Work modes, unifies token quota across plansAnnounced
Google unveils StreamVibe video agent, but benchmark shows models miss help momentsResearch
Meta's ad revenue growth outpaces Google search, widest gap since 2021
Cisco Talos Finds Volta-Autodoxer AI‑Powered Infostealer

Get this every morning, written for your product.

Deltaday reads the whole AI news cycle and tells you what changed, whether it's real yet, and what to do about it.

Request an inviteSee how it works