4 papers · 1 filter
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution
Yunhao Chen, Xin Wang, Yixu Wang +6
AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model interactions, agent behavior…
SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
Jiaqi Yu, Xin Wang, Yixu Wang +4
Large language models increasingly stream long, reasoning-intensive responses in real time, making when to moderate as critical as whether to moderate. Existing guardrails fall int…
SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
Yujiong Shen, Yajie Yang, Zhiheng Xi +17
Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-specific knowledge. Yet, current benchmarks largely overlook agents' ability to orches…
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
Yunhao Chen, Xin Wang, Juncheng Li +5
Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space…