AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 6 of 21 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
The challenges of reliable asynchronous task execution in LLM agents are highlighted and the need to evaluate how agents handle incoming results alongside end-to-end task success is highlighted.
This work proposes SafePO, a reinforcement learning algorithm for refining violation identification while balancing explanatory reasoning and final verdicts, and develops AdaGuard, a family of 0.6B, 4B, and 8B guard models that assess agent trajectories under policies supplied at inference time.
The benchmark evaluates whether agents can recognize and interrupt harm arising from accumulated context, repeated tool use, intermediate actions, and dependencies across steps, and indicates that current systems remain highly vulnerable.
PoisonedEvolution is introduced, a trajectory-poisoning attack on self-evolving skill systems that exposes evidence promotion as a security boundary for self-evolving agents.
HazardAuditor is introduced, an execution-grounded framework that runs heterogeneous agents in controlled environments and normalizes their interactions into a canonical event representation for cross-framework supervision, and observes that token-level post-training objectives create a structural mismatch for generati...
SKILLTRACE is presented, a multi-trace provenance auditing framework for LLM-agent skill reuse that represents the Operational Trace as a Skill Operational Graph (SOG) that captures activation, procedure, and resource-flow structure.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.