论文 AID-Guard: Stateful Authorization for Delegated Agent Effects
论文 Specification Portability Across LLM Development Agents: Cross-Agent Compatibility in Specification-Driven Software Migration
论文 Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents
论文 Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response
论文 When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs
论文 From Detection to Action: Using LLM Agents for Fault-Tolerant Control