AgentHijack Benchmark

What is AgentHijack?

Evaluates the robustness of computer use agents under common environment corruptions such as pop-ups, resolution changes, and competing applications. The…

Released

2026-05-25

Evaluates

Agents, Agents & Tool Use, General AI, Robustness

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.25707

AgentHijack paper and code

• Paper https://arxiv.org/abs/2605.25707
• Code https://github.com/tmlr-group/AgentHijack
• Website https://AgentHijack.github.io

Which sources cite AgentHijack?

• AgentHijack

Related Agents, Agents & Tool Use, General AI, Robustness benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench
• ActiveVision