20 papers
KedgeFlow: A Programmable Control Plane for Enterprise AI Agents
Jun He, Deying Yu
Enterprise AI agents can execute altered versions of approved actions, concurrently reuse the same permission, or retry operations whose responses were lost. These failures arise w…
Before Agents Act: Assurance-Aware Semantic Scheduling for Evidence Acquisition in Distributed Systems
Jun He, Deying Yu
Tool-using agents can initiate consequential infrastructure changes, yet evidence required for admission may expire while other checks run or depend on a shared fault domain. We fo…
Cognitive Admission Control: Risk-Conditioned Assurance for Consequential Actions in Agentic Distributed Systems
Jun He, Deying Yu
In agentic distributed systems, an agent may be authorized to mutate external infrastructure while lacking evidence that the mutation is ready to execute. Cognitive Admission Contr…
Stored Is Not Supported: Typed Provenance and Assertion Guardrails for Persistent AI Agents
Jun He, Deying Yu
Persistent AI agents construct autobiographical state through reflection, retrieval, and consolidation. Persistence changes availability, not epistemic standing: stored or retrieve…
When AI Agents Commit: Cognitive Serializability Across Data, Evidence, Policy, and Authority
Jun He, Deying Yu
Autonomous agents derive concrete mutations from database reads, retrieved evidence, policy, beliefs, and delegated authority. Those inputs may change while reasoning is in progres…
The Situated Identity Test: Distinguishing Persistent Cognitive Identity from Persona Imitation
Jun He, Deying Yu
Large language models can convincingly adopt personas, recall past dialogues, and weave rich autobiographies. Yet this conversational eloquence conceals a fundamental attribution p…
The Illusion of Independent Quorums: Epistemic Fault Domains and Correlated Cognitive Failures in Agentic Quorums
Jun He, Deying Yu
Multi-agent quorums are widely used to authorize high-stakes infrastructure and policy mutations, yet distinct reviewers often share upstream telemetry, documents, or tool backends…
Agent-Native Telemetry: Verifiable State-Delta Evidence for Autonomous Operations
Jun He, Deying Yu
Operational telemetry is predominantly engineered for human reading: systems repeatedly serialize verbose prose, static keys, and redundant context across billions of log lines. As…
Beyond Memory: A Transactional Continuity Kernel for Long-Lived AI Agents
Jun He, Deying Yu
Persistent AI agents accumulate versioned state across long horizons, but storage retention alone does not identify authoritative state. Without an explicit control plane, unmediat…
The Honest Quorum Problem: Epistemic Byzantine Fault Tolerance for Agentic Infrastructure
Jun He, Deying Yu
State machine replication (SMR) and Byzantine fault-tolerant (BFT) consensus guarantee agreement despite a bounded number of arbitrary, colluding faulty participants. However, thes…
Replicating Belief, Not Bits: Epistemic State Replication for Agentic Systems
Jun He, Deying Yu
In distributed systems, the classical State Machine Replication (SMR) model assumes that correct replicas execute deterministic transitions to yield identical bitwise states. Howev…
Sovereign Execution Broker: Enforcing Certificate-Bound Authority in Agentic Control Planes
Jun He, Deying Yu
Autonomous agents are increasingly connected to cloud, deployment, and data-control workflows, but production mutation authority should not reside inside non-deterministic reasonin…
Sovereign Assurance Boundary: Certificate-Bound Admission for Agentic Infrastructure
Jun He, Deying Yu
Agentic infrastructure introduces a critical control-plane authorization problem: non-deterministic reasoning systems can propose high-stakes mutations to production resources, yet…
Semantic Quorum Assurance: Collective Certification for Non-Deterministic AI Infrastructure
Jun He, Deying Yu
As large language model (LLM) agents are integrated into autonomous cloud operations, distributed systems face a semantic reliability problem: proposer agents can generate producti…
Post-Deterministic Distributed Systems: A New Foundation for Trustworthy Autonomous Infrastructure
Jun He, Deying Yu
For decades, distributed systems have typically assumed that correct participants execute protocol-specified behavior with stable, externally defined, and deterministic semantics.…
Protocol-Driven Development: Governing Generated Software Through Invariants and Continuous Evidence
Jun He, Deying Yu
Automated program synthesis lowers the cost of producing implementations but introduces a harder governance problem: determining which generated artifacts are admissible. Natural-l…
Verifiable Agentic Infrastructure: Proof-Derived Authorization for Sovereign AI Systems
Jun He, Deying Yu
Modern cloud and enterprise systems rely on identity-centric authorization, assuming that callers possessing valid credentials are safe to execute commands. The emergence of autono…
Core-Halo Decomposition: Decentralizing Large-Scale Fixed-Point Problems
Haixiang, Yang Xu, Jiefu Zhang +4
We study solving large-scale fixed-point equation \(x^\star=\bar F(x^\star)\) with decomposition. Standard strict decomposition assigns each agent a disjoint block and evaluates up…
Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World Systems
Jun He, Deying Yu
Large language model (LLM) agents increasingly issue API calls that mutate real systems, yet many current architectures pass stochastic model outputs directly to execution layers.…
Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection
Zi Liang, Qipeng Xie, Jun He +7
Recent advancements in Large Language Models (LLMs) have sparked interest in their application to Static Application Security Testing (SAST), primarily due to their superior contex…