# StressWeb: A Diagnostic Benchmark for Web Agent Robustness under Realistic Interaction Variability

arXiv: https://arxiv.org/abs/2604.16385 · HTML: https://mlsanity.com/paper/2604.16385/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 16 of 16)

- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2505.16421/) (2025)
- [A Survey of WebAgents: Towards Next-Generation AI Agents for Web Automation with Large Foundation Models](https://mlsanity.com/paper/2503.23350/) (2025)
- [DeepShop: A Benchmark for Deep Research Shopping Agents](https://mlsanity.com/paper/2506.02839/) (2025)
- [REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites](https://mlsanity.com/paper/2504.11543/) (2025)
- [MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments](https://mlsanity.com/paper/2506.01616/) (2025)
- [WebMall -- A Multi-Shop Benchmark for Evaluating Web Agents](https://mlsanity.com/paper/2508.13024/) (2025)
- [WAREX: Web Agent Reliability Evaluation on Existing Benchmarks](https://mlsanity.com/paper/2510.03285/) (2025)
- [BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks](https://mlsanity.com/paper/2510.02418/) (2025)
- [The Hidden Dangers of Browsing AI Agents](https://mlsanity.com/paper/2505.13076/) (2025)
- [Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning](https://mlsanity.com/paper/2601.03190/) (2026)
- [BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning](https://mlsanity.com/paper/2601.09172/) (2026)
- [Special-Character Adversarial Attacks on Open-Source Language Model](https://mlsanity.com/paper/2508.14070/) (2025)
- [PopSweeper: Automatically Detecting and Resolving App-Blocking Pop-Ups to Assist Automated Mobile GUI Testing](https://mlsanity.com/paper/2412.02933/) (2024)

## Built on by (most cited first, 2 of 2)

- [Signal-Driven Observation for Long-Horizon Web Agents](https://mlsanity.com/paper/2606.06708/) (2026)
- [When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents](https://mlsanity.com/paper/2610.19910/) (2026)

## Abstract (arXiv)

Large language model-based web agents have demonstrated strong performance on realistic web interaction tasks. However, existing evaluations are predominantly conducted under relatively stable and well-behaved interaction conditions, which may overestimate agent robustness. High task success in such idealized settings does not necessarily reflect performance under realistic web interaction. To address this limitation, we introduce a diagnostic stress-testing benchmark for web agents. We first construct realistic and controllable web environments that provide clean and stable interaction workflows as reference baselines. We then introduce structured and controlled perturbations that emulate interaction variability, including shifting layouts, altered interaction semantics, and execution disruptions. By comparing agent behavior between clean and perturbed settings, our framework enables systematic diagnosis of robustness under what-if interaction scenarios. Through extensive evaluation of state-of-the-art multimodal web agents, we show that stress-based evaluation exposes failure modes and substantial robustness gaps that remain hidden under clean benchmark conditions.