arXiv 2610.13623 · cs.CR · 2026-10-09
APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces
Ziyi Yang, Adel Bibi, Guohao Li, Bernard Ghanem, Carlos Hinojosa
King Abdullah University of Science and Technology
In latest · #298 Added on 2026-10-21
One-line takeaway
APEX-Harm tests finance, consulting and legal agents against prompt and script injection in large shared workspaces.
APEX-Harm 在含上百个文件的共享工作区里，测试金融、咨询、法律 Agent 抵御提示和脚本注入的能力。
Read on arXiv PDF Hugging Face discussion Code
Topics & disciplines
More on Safety & interpretability
- Behavioral Compositionality of Sparse Autoencoder Representations ▲110
- DecepEval: A Benchmark for Evaluating Deception in LLM Agents ▲85
- Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics ▲55
- U-Space: Uncovering When and Why Uncertainty Arises in Language Models ▲54
- Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures ▲29
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.