AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

UINavBench: A Framework for Comprehensive Evaluation of Interactive Digital Agents

Harsh Agrawal, Eldon Schoop, Xinlei Pan, Anuj Mahajan, Ari Seff, Di Feng, Ruijia Cheng, Andres Romero Mier Y Teran, Esteban Gomez, Abhishek Sundararajan, Forrest Huang, Amanda Swearngin and 3 more

ICCV 2025 · Multi-agent systems and games › LLM agents · approach: GUI agent memory and trajectories · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add simplified text representation of detected UI elements to set-of-marks prompting (ablation)ReACT agent (GPT-4o) · UINavBenchEpisode Success: 25.8% -> 31.8%Improved
add Reflexion self-critique with a VLM critic (ablation)ReACT + Text agent (GPT-4o) · UINavBenchEpisode Success: 31.8% -> 40.5%Improved
replace heuristic SoM grounding with the UGround grounding model (ablation)Reflexion + Text agent · UINavBenchEpisode Success: 40.5% -> 33.5%Hurt
use end-to-end UI-TARS-72B instead of modular GPT-4o plannerUINavBench agents · UINavBenchEpisode Success: 40.5% -> 11%Hurt
increase task complexity from simple to complex with deep navigationReflexion + Text · UINavBenchsuccess: 11/14 (79%) -> 4/36 (11%)Hurt
require visual understanding instead of text-only perceptionReflexion + Text · UINavBenchEpisode Success: 80% -> 7.7%Hurt
require world knowledge outside the environmentReflexion + Text · UINavBenchEpisode Success: 47.7% -> 13.3%Hurt
Reflexion on data entry tasks (ablation)Reflexion + Text · UINavBench data entry tasksEpisode Success: 10.6% -> 8.5%No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy