arXiv AI
LanG 2.0: Energy-Efficient Agentic AI for Semi-Automated Security Operations at Scale
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 23
A Governance-Aware Large Language Model Orchestrated Agentic Digital Twin for Transmission System Operator Control Room Decision Support
arXiv:2609.22476v1 Announce Type: cross Abstract: Transmission system operators face rising complexity from renewable integration, reduced inertia, and tighter security margins. Large language models...
arXiv AI
Oct 27
SentryBench: A Cost-Sensitive Benchmark for Adversarial Robustness of Tool-Using LLM Agents in Public-Safety Deployments
SentryBench is a cost‑sensitive benchmark designed to evaluate large language model agents that use tools in public‑safety contexts. It measures agents on a frontier that jointly considers attack success, over‑refusal (missing real emergencies), and over‑reaction (unwarranted actions) under adversarial tool use, using scenarios grounded in real emergency‑call transcripts and disaster messages. The study shows that naive caution leads to high harm, while a targeted trust‑gate wrapper reduces harm across models and defenses.
arXiv AI
Jul 31
SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response
arXiv:2607. 26791v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities.
arXiv AI
Jun 12
The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements
arXiv:2606. 12797v1 Announce Type: new Abstract: Agentic large language model systems that autonomously invoke tools, maintain persistent memory, and execute multi-step plans are increasingly deployed in public-facing domains, including government services, healthcare triage, and financial advising.
arXiv AI
Sep 10
AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories
arXiv:2609.06972v1 Announce Type: cross Abstract: LLM agents complete tasks by issuing sequences of tool calls, and every observation they read is a channel through which an indirect prompt injection...
arXiv Computation and Language
Oct 27
"I Strongly Suspect This Website Is a Scam": Benchmarking PII Leakage and Detection without Defense in Autonomous Web Agents
arXiv:2606.00497v2 Announce Type: replace-cross Abstract: Deceptive web content, widely instantiated across the internet and commonly known as \textit{social-engineering attacks}, manipulates autonom...