🔻Victoria Hand – S.H.I.E.L.D. Agent 🔻
Stepping into the shoes (and sharp suit) of one of Marvel’s most complex and underrated characters: Victoria Hand.

#VictoriaHand #SHIELDAgent #MarvelCosplay #CatleenCosplay #WomenOfMarvel #MarvelComics #AgentsOfSHIELD #MarvelVillain #StrategistVibes #cosplay

Some more Shawn cause he's fun to draw.
#marveloc #marvelshield #shieldoc #shieldagent #oc

#DoomsDay #IronMan #AvengersDoomsday
Avengers Fan Theories go Wild!
#OGAvenger #ShieldAgent #Level7
🦸‍♂️😱🤖

recall of 90.1%. Additionally, ShieldAgent reduces API queries by 64.7% and inference time by 58.2%, demonstrating its high precision and efficiency in safeguarding agents. [7/7 of https://arxiv.org/abs/2503.22738v1]

trajectories, collected via SOTA attacks across 6 web environments and 7 risk categories. Experiments show that ShieldAgent achieves SOTA on ShieldAgent-Bench and three existing benchmarks, outperforming prior methods by 11.3% on average with a high [6/7 of https://arxiv.org/abs/2503.22738v1]

comprehensive tool library and executable code for formal verification. In addition, given the lack of guardrail benchmarks for agents, we introduce ShieldAgent-Bench, a dataset with 3K safety-related pairs of agent instructions and action [5/7 of https://arxiv.org/abs/2503.22738v1]

from policy documents and structuring them into a set of action-based probabilistic rule circuits. Given the action trajectory of the protected agent, ShieldAgent retrieves relevant rule circuits and generates a shielding plan, leveraging its [4/7 of https://arxiv.org/abs/2503.22738v1]

first guardrail agent designed to enforce explicit safety policy compliance for the action trajectory of other protected agents through logical reasoning. Specifically, ShieldAgent first constructs a safety policy model by extracting verifiable rules [3/7 of https://arxiv.org/abs/2503.22738v1]

can result in severe consequences such as privacy breaches and financial losses. More critically, existing guardrails for LLMs are not applicable due to the complex and dynamic nature of agents. To tackle these challenges, we propose ShieldAgent, the [2/7 of https://arxiv.org/abs/2503.22738v1]

Zhaorun Chen, Mintong Kang, Bo Li: ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning https://arxiv.org/abs/2503.22738 https://arxiv.org/pdf/2503.22738 https://arxiv.org/html/2503.22738