FlowSteer is a prompt-only attack that biases multi-agent LLM workflow planning to propagate malicious signals, raising success rates by up to 55%, with FlowGuard as an input-side defense reducing it by up to 34%.
Herd behavior: Investigating peer influence in llm-based multi-agent systems
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Large language models exhibit normative conformity in addition to informational conformity, and subtle social context can direct which group they conform to.
A systematic audit of LLM-based AI societies finds that 89.7% of 39 studies violate at least one of six PIMMUR validity principles, with reproductions showing that many claimed collective behaviors disappear when controls are tightened.
Introduces EPC-AW to mitigate epistemic miscalibration in LLM multi-agent planning via consistency-based selection and refinement, reporting 9.75% average success improvement.
Evaluates eight frontier MLLMs on a new dataset of 200 annotated Chinese short videos for detecting deceptive patterns and cognitive biases, with Gemini-2.5-Pro scoring highest at 71.5/100 belief in multimodal setting.
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
-
FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
FlowSteer is a prompt-only attack that biases multi-agent LLM workflow planning to propagate malicious signals, raising success rates by up to 55%, with FlowGuard as an input-side defense reducing it by up to 34%.
-
Large Language Models Exhibit Normative Conformity
Large language models exhibit normative conformity in addition to informational conformity, and subtle social context can direct which group they conform to.
-
The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies
A systematic audit of LLM-based AI societies finds that 89.7% of 39 studies violate at least one of six PIMMUR validity principles, with reproductions showing that many claimed collective behaviors disappear when controls are tightened.
-
When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems
Introduces EPC-AW to mitigate epistemic miscalibration in LLM multi-agent planning via consistency-based selection and refinement, reporting 9.75% average success improvement.
-
Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video Misinformation
Evaluates eight frontier MLLMs on a new dataset of 200 annotated Chinese short videos for detecting deceptive patterns and cognitive biases, with Gemini-2.5-Pro scoring highest at 71.5/100 belief in multimodal setting.
-
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.