3 papers
cs.CR2026
Will the Agent Recuse, and Will It Stop? Measuring LLM-Agent Compliance with In-Band Governance Signals at the Access Door and Mid-Flight
Thamilvendhan Munirathinam
As autonomous LLM agents hold real credentials and operate infrastructure without a human in the loop, operators cannot tell an agent a resource is off-limits, or ask a running age…
cs.CR2026
memorywire: A Vendor-Neutral Wire Format for Agent Memory Operations
Thamilvendhan Munirathinam
Agent-memory frameworks -- mem0, Letta/MemGPT, Cognee, Zep/Graphiti, MemoryOS, MemTensor -- each ship their own SDK, storage layout, and operational vocabulary. There is no shared…
cs.CR2026
Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection
Thamilvendhan Munirathinam
Current open-source prompt-injection detectors converge on two architectural choices: regular-expression pattern matching and fine-tuned transformer classifiers. Both share failure…