arXiv AI
Jul 8
Proof of Execution: Runtime Verification for Governed AI Agent Actions
arXiv:2607. 05397v1 Announce Type: cross Abstract: Agent systems increasingly execute rather than advise.
MIRROR: Multipath Quorum Integrity for LLM Multi-Agent Communication
Related stories
arXiv AI
Jun 16
The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs
arXiv:2606. 16358v1 Announce Type: cross Abstract: Agents increasingly access large language models (LLMs) through API routers.
arXiv AI
Jun 19
Trustworthy Multi-Agent Systems: Mitigating Semantic Drift with the Argent Signaling Protocol
arXiv:2606. 19356v1 Announce Type: cross Abstract: When multi-agent LLM systems produce bad answers, not all failures are equal: some answers are grounded in the right material but incomplete, while others are simply ungrounded and should be stopped.
arXiv AI
Jun 8
From Privacy to Workflow Integrity: Communication-Graph Metadata in Autonomous Agent Interoperability
arXiv:2606. 07150v1 Announce Type: cross Abstract: Agent-interoperability protocols such as A2A and MCP standardize what agents say to one another, but assume address-based transport over HTTP(S).
arXiv AI
Jun 30
MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems
arXiv:2606. 30602v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used to automate complex, distributed workflows.
arXiv Computation and Language
Aug 25
Decomposition Attacks Across Unlinkable Identities: Limits of Stateful Defenses for LLM Services
arXiv:2608.17445v2 Announce Type: replace-cross Abstract: Most large language model services use stateless defenses, which judge only the current request, to refuse harmful tasks. Decomposition attac...
arXiv Machine Learning
Jul 20
The Honest Quorum Problem: Epistemic Byzantine Fault Tolerance for Agentic Infrastructure
arXiv:2607. 16109v1 Announce Type: new Abstract: State machine replication (SMR) and Byzantine fault-tolerant (BFT) consensus guarantee agreement despite a bounded number of arbitrary, colluding faulty participants.
arXiv AI
Sep 2
Delegation Without Trust: An Empirical Gap Analysis of Identity, Authorization, and Runtime Governance in Multi-Agent LLM Systems
The paper examines the security challenges of delegating authority to autonomous LLM agents that act on users’ behalf. It introduces a threat model with four adversaries and eight security requirements, demonstrates that current frameworks (LangGraph, CrewAI, AutoGen, MCP) fail to meet these standards, and presents an authorization broker that blocks all identified threats with minimal overhead. The broker is shown to resist numerous attacks and limits compromised sub‑agents to their delegated tasks, and its principles are implemented in VotalAI’s LLM Shield.
arXiv AI
Jul 23
Will the Agent Recuse, and Will It Stop? Measuring LLM-Agent Compliance with In-Band Governance Signals at the Access Door and Mid-Flight
arXiv:2606. 06460v3 Announce Type: replace-cross Abstract: Autonomous LLM agents increasingly hold real credentials and operate infrastructure with no human in the loop, yet operators have no standard way to tell an agent a resource is off-limits, or to ask a running agent to stand down: access controls either admit it or hard-fail it.
arXiv Machine Learning
Aug 11
RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough
arXiv:2608. 07583v1 Announce Type: cross Abstract: Multi-agent LLM systems route among model-backed advisors, yet a deployer rarely knows before shipping whether routing will help at all.
arXiv AI
Jun 9
Semantic Quorum Assurance: Collective Certification for Non-Deterministic AI Infrastructure
arXiv:2606. 08021v1 Announce Type: cross Abstract: As large language model (LLM) agents are integrated into autonomous cloud operations, distributed systems face a semantic reliability problem: proposer agents can generate production mutations, such as modifying IAM policies, opening firewall security groups, or executing data exports, that are syntactically valid and statically authorized but operationally unsafe.
arXiv AI
Jun 2
Attested Tool-Server Admission: A Security Extension to the Model Context Protocol
arXiv:2605. 24248v2 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) standardizes how a large-language-model (LLM) agent and an external tool server exchange messages, but not trust: a host reads a server's self-declared tool list and dispatches calls, with no notion of which servers it may use, at what sensitivity, or which of a server's tools are in bounds.