Paper Detail

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

Yunhao Chen, Xin Wang, Yixu Wang, Yi Liu, Jie Li, Yan Teng, Xingjun Ma, Xia Hu, Yu-Gang Jiang

huggingface Score 11.0

Published 2026-08-01 · First seen 2026-08-13

General AI

Abstract

AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior is mediated through a shared state that is repeatedly modified and reused across long-horizon workflows. Current safety benchmarks often fail to capture these cumulative risks because they focus on short, static tasks. To address these limitations, we introduce OpenART, an open-ended arena for scalable agent red teaming through environment evolution. OpenART provides over 10,000 validated stateful scenarios across 50 domains, drawing from a pool of more than 500,000 tools and skills. These tasks require a median of 97 tool calls and enable unified evaluation across 75 different agent-model configurations. To systematically explore these evolving attack surfaces, we propose the Evolutionary Markov Hypergraph Attack (EMHA). EMHA is a black-box policy that performs feedback-driven environment evolution by coordinating authorized state transitions without requiring parameter updates. Throughout the evaluation, task objectives remain fixed while only the environment state changes. Across all configurations, EMHA achieves a pooled Attack Success Rate (ASR) of 85.0%. Its advantage over instruction-only evolution increases from approximately 2% on simple environments to over 17% on the most complex ones, demonstrating that environment evolution increasingly exposes safety failures as task complexity grows. Furthermore, our analysis shows that the specific runtime implementation of an agent explains a significant portion of safety variation beyond the underlying model's capabilities. These results establish OpenART as a scalable foundation for studying agent safety in complex, evolving environments.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{chen2026openart,
  title = {OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution},
  author = {Yunhao Chen and Xin Wang and Yixu Wang and Yi Liu and Jie Li and Yan Teng and Xingjun Ma and Xia Hu and Yu-Gang Jiang},
  year = {2026},
  abstract = {AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior is mediated through a shared state that is repeatedly modified and reused across long-horizon workflows. Current safety benchmarks often fail to capture these cumulative risks because they focus on short, static tasks. To address these limitations, we introduce OpenART, an open-ended arena for scalable agent red teamin},
  url = {https://huggingface.co/papers/2608.00677},
  keywords = {OpenART, stateful scenarios, Evolutionary Markov Hypergraph Attack, EMHA, black-box policy, environment evolution, authorized state transitions, Attack Success Rate, ASR, runtime implementation, code available, huggingface daily},
  eprint = {2608.00677},
  archiveprefix = {arXiv},
}

Metadata

{}