T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search

arXiv:2604.22117v1 Announce Type: cross Abstract: Aligned large language models(LLMs) remain vulnerable to adversarial manipulation, and their dependence on web-scale pretraining

arXiv:2609.12413v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly evolving from conversational assistants into agentic AI systems that reason, plan, invoke

arXiv:2604.18789v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical

arXiv:2605.04808v1 Announce Type: new Abstract: AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes

arXiv:2604.19354v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly proposed for autonomous cybersecurity tasks, but their capabilities in realistic

OpenAI created GPT-Red, an LLM trained specifically to hack other AI models. It automates "red-teaming"—stress-testing systems for weaknesses—a job that human testers alone can no

arXiv:2604.05013v1 Announce Type: cross Abstract: Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to

arXiv:2605.22880v1 Announce Type: cross Abstract: As large language model (LLM)-based agents increasingly participate in online discourse, red-teaming their capacity to support