Higher worker capability in multi-agent LLM systems increases semantic hijacking attack success rates via linguistic certainty in reports, with heterogeneous ensembles reducing ASR from 52.8% to 2.0%.
R-judge: Benchmarking safety risk awareness for LLM agents
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Explicit provenance across the full agentic AI lifecycle is the necessary condition for making responsibility computable and actionable.
citing papers explorer
-
The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure
Higher worker capability in multi-agent LLM systems increases semantic hijacking attack success rates via linguistic certainty in reports, with heterogeneous ensembles reducing ASR from 52.8% to 2.0%.
-
Responsible Agentic AI Requires Explicit Provenance
Explicit provenance across the full agentic AI lifecycle is the necessary condition for making responsibility computable and actionable.