EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants

Hugging Face Daily Papers Papers

Summary

EvoGenUI-Bench introduces a benchmark for evaluating LLMs as multi-turn generative UI assistants, focusing on interface maintenance across 150 tasks with challenges in state propagation and external grounding.

Large language models can generate interactive web interfaces, but reliable generative UI requires maintaining an executable artifact as user requests evolve. We introduce EvoGenUI-Bench, a benchmark for multi-turn interface maintenance comprising 150 five-turn tasks and 750 turns across three scenarios: information presentation, executable interaction, and tool-grounded external state. We execute generated artifacts in a browser and evaluate them using screenshots, source and DOM evidence, actor traces, and runtime logs. Beyond turn-level and episode-level success, we measure cross-turn retention with Adjacent Pass Retention. Across eight models, even the strongest achieves 74.9% Turn Pass while completing only 37.3% of five-turn episodes; APR further falls to 52.4% on tool-grounded tasks. Diagnostic analysis shows that presentation failures center on information architecture, interaction failures on derived-state propagation and affordance binding, and tool-grounded failures additionally involve external-state grounding and requirement decomposition. These results reframe generative UI evaluation from judging isolated outputs to testing whether interface behavior, derived state, external state, and assistant claims remain synchronized as the artifact evolves.
Original Article
View Cached Full Text

Cached at: 09/01/26, 11:41 AM

Paper page - EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants

Source: https://huggingface.co/papers/2608.29387

Abstract

Largelanguagemodelscangenerateinteractivewebinterfaces,butreliablegenerativeUIrequiresmaintaininganexecutableartifactasuserrequestsevolve.WeintroduceEvoGenUI-Bench,abenchmarkformulti-turninterfacemaintenancecomprising150five-turntasksand750turnsacrossthreescenarios:informationpresentation,executableinteraction,andtool-groundedexternalstate.Weexecutegeneratedartifactsinabrowserandevaluatethemusingscreenshots,sourceandDOMevidence,actortraces,andruntimelogs.Beyondturn-levelandepisode-levelsuccess,wemeasurecross-turnretentionwithAdjacentPassRetention.Acrosseightmodels,eventhestrongestachieves74.9%TurnPasswhilecompletingonly37.3%offive-turnepisodes;APRfurtherfallsto52.4%ontool-groundedtasks.Diagnosticanalysisshowsthatpresentationfailurescenteroninformationarchitecture,interactionfailuresonderived-statepropagationandaffordancebinding,andtool-groundedfailuresadditionallyinvolveexternal-stategroundingandrequirementdecomposition.TheseresultsreframegenerativeUIevaluationfromjudgingisolatedoutputstotestingwhetherinterfacebehavior,derivedstate,externalstate,andassistantclaimsremainsynchronizedastheartifactevolves.

View arXiv pageView PDFGitHub0Add to collection

Get this paper in your agent:

hf papers read 2608\.29387

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.29387 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.29387 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.29387 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Looks Right, Works Right: A Project-Level Benchmark for Multi-Screen Mobile App Generation

arXiv cs.AI

MobileForge is a benchmark for project-level multi-screen mobile app generation, evaluating multimodal LLMs on build success, cross-page navigation, visual fidelity, maintainability, and efficiency. Experiments on six frontier multimodal LLMs show current models can compile and reach pages but still struggle with interactive navigation and visual quality.