Policy dependency / Stack layer
Reason Less, Verify More: Deterministic Gates Catch a Silent Policy-Violation Failure in Tool-Using Agents
arXiv
Stack layer / Threat pattern
Open-Source Multi-Agent Firewall Intercepts Both HTTP(S) and WebSocket LLM Traffic
arXiv
Stack layer / Threat pattern
Mitigating Taint-Style MCP Server Vulnerabilities Without Touching Server Code (SPELLSMITH)
arXiv
Policy dependency / Threat pattern
Prismata Confines Cross-Site Prompt Injection by Treating Web Agents Like an XSS Problem
arXiv
Stack layer / Contrast
Tool-Making Agents Compile Repeated SOP Steps Into Versioned Tools Before Deployment
arXiv
Stack layer
MCP-Grounded Agent Pipeline Converts Legacy Docs to NIST OSCAL for Continuous Compliance
arXiv
Update thread / Follow-up thread
EvoAgentBench: A Benchmark That Isolates Whether Agents Can Turn Past Sessions Into Reusable Procedures
arXiv
Stack layer
TTHE: Test-Time Harness Evolution Lets Agents Rewrite Their Own Scaffolding Mid-Run
arXiv