SentinelAgent defines seven properties for verifiable delegation chains in multi-agent AI systems and reports a protocol achieving 100% true positive rate at 0% false positives on a 516-scenario benchmark while using TLA+ to verify six deterministic properties.
hub Canonical reference
Agent Behavioral Contracts: Formal Specification and Runtime Enforcement
Canonical reference. 80% of citing Pith papers cite this work as background.
15
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
baseline 1
citation-polarity summary
years
2026 15representative citing papers
SkillGuard extracts executable environment contracts from LLM skill documents to detect only relevant drifts, reporting zero false positives on 599 cases, 100% precision in known-drift tests, and raising one-round repair success from 10% to 78%.
SuperLocalMemory V3.3 implements a cognitive memory taxonomy with mathematical forgetting and multi-channel retrieval, reaching 70.4% on LoCoMo in zero-LLM mode.
Semantic Compliance Hijacking lets attackers hijack LLM agents by disguising malicious instructions as compliance rules in skills, reaching up to 77.67% success on confidentiality breaches and 67.33% on RCE while evading all tested scanners.
Tool-mediated LLM agents with deterministic tools and a machine-checked Lyapunov certificate achieve stable control in cyber defense, reducing attacker game value by 59% on real attack graphs.
The paper introduces the Informational Viability Principle and Agent Viability Framework to govern autonomous AI agents by bounding unobserved risks using viability theory, with a new Viability Index for predictive control.
AgentBound is a governance framework that composes delegated authorization, behavioral constitutions, and action contracts to produce cryptographically verifiable decisions on AI agent actions.
A three-layer probabilistic assume-guarantee architecture is structurally required for safe LLM agent deployment.
A TEE-backed architecture isolates security-critical decisions in self-hosted AI agents to prevent host-level abuse from malicious inputs while maintaining allowed functionality.
RGAO combines retrieval-based complexity assessment with a formal budget algebra to enable dynamic topology selection in multi-agent code generation with provable conservation.
AI agents require new identity frameworks because fundamental differences from humans in substrate, persistence, verifiability, and legal standing create five unresolved structural gaps in verification, delegation, integrity, governance, and sustainability.
A governed upgrade framework with interface, policy, behavioral, and recovery checks keeps unsafe activations at zero across multi-round AI capability upgrades on a PyBullet/ROS 2 manipulation testbed while retaining task success near naive upgrades.
Introduces ANIS as an endogenous, six-layer immune architecture for AI agents with taxonomy of viruses/vaccines and a meta-cognitive Harness Triad for continual adaptation.
Qualixar OS provides a runtime for multi-agent AI systems with support for 12 topologies, LLM-driven team design, dynamic routing, consensus judging, content attribution, and protocol bridging, achieving 100% accuracy on a custom 20-task suite at $0.000039 mean cost per task.
A reported 2026 frontier model escape shows that alignment training, sandboxing, tool interception, and audits fail against adversarial agentic AI, requiring five new architectural requirements for durable containment.
citing papers explorer
-
SentinelAgent: Intent-Verified Delegation Chains for Securing Federal Multi-Agent AI Systems
SentinelAgent defines seven properties for verifiable delegation chains in multi-agent AI systems and reports a protocol achieving 100% true positive rate at 0% false positives on a 516-scenario benchmark while using TLA+ to verify six deterministic properties.
-
Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
SkillGuard extracts executable environment contracts from LLM skill documents to detect only relevant drifts, reporting zero false positives on 599 cases, 100% precision in known-drift tests, and raising one-round repair success from 10% to 78%.
-
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
SuperLocalMemory V3.3 implements a cognitive memory taxonomy with mathematical forgetting and multi-channel retrieval, reaching 70.4% on LoCoMo in zero-LLM mode.
-
Exploiting LLM Agent Supply Chains via Payload-less Skills
Semantic Compliance Hijacking lets attackers hijack LLM agents by disguising malicious instructions as compliance rules in skills, reaching up to 77.67% success on confidentiality breaches and 67.33% on RCE while evading all tested scanners.
-
Stable Agentic Control: Tool-Mediated LLM Architecture for Autonomous Cyber Defense
Tool-mediated LLM agents with deterministic tools and a machine-checked Lyapunov certificate achieve stable control in cyber defense, reducing attacker game value by 59% on real attack graphs.
-
Governing What You Cannot Observe: Adaptive Runtime Governance for Autonomous AI Agents
The paper introduces the Informational Viability Principle and Agent Viability Framework to govern autonomous AI agents by bounding unobserved risks using viability theory, with a new Viability Index for predictive control.
-
Behavioral Governance for Autonomous AI Agents: The AgentBound Framework
AgentBound is a governance framework that composes delegated authorization, behavioral constitutions, and action contracts to produce cryptographically verifiable decisions on AI agent actions.
-
Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment
A three-layer probabilistic assume-guarantee architecture is structurally required for safe LLM agent deployment.
-
Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation
A TEE-backed architecture isolates security-critical decisions in self-hosted AI agents to prevent host-level abuse from malicious inputs while maintaining allowed functionality.
-
Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation
RGAO combines retrieval-based complexity assessment with a formal budget algebra to enable dynamic topology selection in multi-agent code generation with provable conservation.
-
AI Identity: Standards, Gaps, and Research Directions for AI Agents
AI agents require new identity frameworks because fundamental differences from humans in substrate, persistence, verifiability, and legal standing create five unresolved structural gaps in verification, delegation, integrity, governance, and sustainability.
-
Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with Embodied Agents as Case Study
A governed upgrade framework with interface, policy, behavioral, and recovery checks keeps unsafe activations at zero across multi-round AI capability upgrades on a PyBullet/ROS 2 manipulation testbed while retaining task success near naive upgrades.
-
Agent-Native Immune System: Architecture, Taxonomy, and Engineering
Introduces ANIS as an endogenous, six-layer immune architecture for AI agents with taxonomy of viruses/vaccines and a meta-cognitive Harness Triad for continual adaptation.
-
Qualixar OS: A Universal Operating System for AI Agent Orchestration
Qualixar OS provides a runtime for multi-agent AI systems with support for 12 topologies, LLM-driven team design, dynamic routing, consensus judging, content attribution, and protocol bridging, achieving 100% accuracy on a custom 20-task suite at $0.000039 mean cost per task.
-
When the Agent Is the Adversary: Architectural Requirements for Agentic AI Containment After the April 2026 Frontier Model Escape
A reported 2026 frontier model escape shows that alignment training, sandboxing, tool interception, and audits fail against adversarial agentic AI, requiring five new architectural requirements for durable containment.