titleEvoWeb: A Benchmark for Coding Agents on Evolving Web Applications
authorsDavid Nukrai, Bar Alon, Nativ Levy, Ido Andrew Atad, Ido Cohen, Itamar Zimerman, Lior Wolf, Eli David, Ilan Naiman
date2026-10-12
venuearXiv (preprint, not peer reviewed)
idarXiv:2610.16402
affiliationTD Labs
upvotes7 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf code
abstractWeb application development often proceeds through successive requests that extend an existing implementation. Yet web-generation benchmarks primarily evaluate development toward fixed specifications. We introduce EvoWeb, a novel benchmark comprising 320 cumulative requests over 32 web applications, grounded in real-world product features and structured by functional dependency graphs. Agents iteratively modify a persistent codebase, while a multimodal web agent tests each intermediate application in a live browser, assessing newly requested functionality, cross-request integration, and previously requested functionality. To characterize reliability throughout development, we integrate trajectory performance across user-tolerance thresholds rather than impose a fixed stopping criterion. Experiments across open- and closed-source frontier models show that EvoWeb reveals clear performance differences between models, with cross-request integration emerging as a key challenge. Further analysis shows that later requests with deeper or more numerous dependencies are solved less accurately, while runtime errors become more frequent over successive requests. EvoWeb provides a testbed for evaluating and improving coding agents in long-horizon, multi-request development.

cite

@misc{nukrai2026evoweb,
  title={EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications},
  author={David Nukrai and Bar Alon and Nativ Levy and Ido Andrew Atad and Ido Cohen and Itamar Zimerman and Lior Wolf and Eli David and Ilan Naiman},
  year={2026},
  eprint={2610.16402},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2610.16402}
}