VLMs preserve linearly separable visual magnitudes and can compare them, yet collapse at symbolic mapping because visual and textual number spaces remain fractured and disjoint.
Beyond Single- Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Boiling the Frog is a new stateful multi-turn benchmark that finds an aggregate 44.4% strict attack success rate for incremental safety violations across nine AI models, with rates ranging from 20.5% to 92.9%.
In agentic AI, safety and fairness are governed by interaction topology rather than model scale or alignment.
The authors introduce agentic microphysics and generative safety to link local agent interactions to population-level risks in agentic AI through a causally explicit framework.
citing papers explorer
-
Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms
VLMs preserve linearly separable visual magnitudes and can compare them, yet collapse at symbolic mapping because visual and textual number spaces remain fractured and disjoint.
-
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety
Boiling the Frog is a new stateful multi-turn benchmark that finds an aggregate 44.4% strict attack success rate for incremental safety violations across nine AI models, with rates ranging from 20.5% to 92.9%.
-
Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment
In agentic AI, safety and fairness are governed by interaction topology rather than model scale or alignment.
-
Agentic Microphysics: A Manifesto for Generative AI Safety
The authors introduce agentic microphysics and generative safety to link local agent interactions to population-level risks in agentic AI through a causally explicit framework.