Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure
Shenghan Zheng, Zonglin Di, Yimin Liu +19
LM-agent benchmarks increasingly function as interactive evaluation infrastructure. Agents observe state, call tools, modify workspaces, submit artifacts, and receive rewards from…
cs.CR2026
Formal Security Analysis of Agent Protocol Composition
Shenghan Zheng, Qifan Zhang, Zheng Zhang +2
AI agent protocols define how agents use tools, delegate work, and coordinate across software systems, but their security requirements remain incomplete and inconsistently enforced…
cs.CR2026
AgentRFC: Security Design Principles and Conformance Testing for Agent Protocols
Shenghan Zheng, Qifan Zhang
AI agent protocols -- including MCP, A2A, ANP, and ACP -- enable autonomous agents to discover capabilities, delegate tasks, and compose services across trust boundaries. Despite m…