Harness-MU is a zero-tuning infrastructure that decouples safety orchestration from language generation in multi-user LLM agents, achieving full privacy preservation on Muses-Bench while improving utility and instruction-following over baselines.
The orchestration of multi-agent systems: Architec- tures, protocols, and enterprise adoption
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 9verdicts
UNVERDICTED 9roles
background 1polarities
background 1representative citing papers
A learned orchestration policy for LLM agents that jointly optimizes task decomposition and selective routing to (model, primitive) pairs, delivering 77% macro pass@1 at 10x lower cost than strong baselines across 13 benchmarks.
Modality-native routing in A2A networks raises task accuracy from 32% to 52% over text-bottleneck baselines on a 50-task benchmark, but only when paired with capable downstream reasoning.
Context Kubernetes formalizes six abstractions for knowledge orchestration in agentic AI, with experiments showing a three-tier permission model blocks all five tested attack scenarios where simpler baselines fail.
Semantic Consensus Framework achieves 100% workflow completion in multi-agent LLM setups by detecting and resolving semantic conflicts, far outperforming existing approaches at 25.1%.
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
A graph-based propagation model for error cascades in LLM multi-agent systems plus a genealogy-graph governance plugin that prevents final infection in at least 89% of runs across tested frameworks.
Agentic AI evaluation and governance lack mechanisms to bind obligations to actions and prove compliance at runtime; a new synthesis framework with ODTA criteria and action-evidence bundles addresses this closure gap.
SS-ZKR is a proposed privacy-preserving semantic routing protocol for multi-agent systems that combines blind intent vectors, adaptive sanitization, and spatial-to-cryptographic policy compilation to enable cross-boundary collaboration without exposing data to routing infrastructure.
citing papers explorer
-
Harness-MU: A Safe, Governed, and Effective Harness for Multi-User LLM Agents
Harness-MU is a zero-tuning infrastructure that decouples safety orchestration from language generation in multi-user LLM agents, achieving full privacy preservation on Muses-Bench while improving utility and instruction-following over baselines.
-
Security Considerations for Multi-agent Systems
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
-
SS-ZKR: Spatial-Semantic Zero-Knowledge Routing for Privacy-Preserving Multi-Agent Collaboration
SS-ZKR is a proposed privacy-preserving semantic routing protocol for multi-agent systems that combines blind intent vectors, adaptive sanitization, and spatial-to-cryptographic policy compilation to enable cross-boundary collaboration without exposing data to routing infrastructure.