MPAC defines a multi-principal agent coordination protocol across Session, Intent, Operation, Conflict, and Governance layers, with 21 message types and state machines, delivering 95% lower coordination overhead in a three-agent code review benchmark.
Time, clocks, and the ordering of events in a distributed system.Communica- tions of the ACM, 21(7):558–565, 1978
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
SRCT models streaming as concurrent reservoir filling with k standby streams, proving harmonic uptime bounds, 3-5x acquisition speedup, monotonic quality convergence, and a prospect-theoretic no-thrash switching rule.
Small clock skews (around 5 ms) cause causality violations in timestamp-based observability of distributed AI inference pipelines while leaving throughput and output correctness unaffected.
citing papers explorer
-
MPAC: A Multi-Principal Agent Coordination Protocol for Interoperable Multi-Agent Collaboration
MPAC defines a multi-principal agent coordination protocol across Session, Intent, Operation, Conflict, and Governance layers, with 21 message types and state machines, delivering 95% lower coordination overhead in a three-agent code review benchmark.
-
The Streaming Reservoir Convergence Theorem: A Prospect-Theoretic Framework for Multi-Provider Adaptive Streaming
SRCT models streaming as concurrent reservoir filling with k standby streams, proving harmonic uptime bounds, 3-5x acquisition speedup, monotonic quality convergence, and a prospect-theoretic no-thrash switching rule.
-
Time, Causality, and Observability Failures in Distributed AI Inference Systems
Small clock skews (around 5 ms) cause causality violations in timestamp-based observability of distributed AI inference pipelines while leaving throughput and output correctness unaffected.