Genesis: Advanced Evolving Attacks for LLM Web Agents
Discover Genesis, a dynamic framework evolving attack strategies to enhance LLM web agent red-teaming and improve security testing effectiveness.
Evaluating Self-Replication Risks in LLM Agents
Explore a new framework assessing self-replication risks in LLM agents, highlighting safety concerns and mitigation strategies for AI deployments.
Retrieval-of-Thought: Boost AI Reasoning Efficiency Fast
Discover Retrieval-of-Thought, a breakthrough AI method that reuses past reasoning to cut latency by 82% and costs by 59% while maintaining accuracy.
Automating Dynamic Programming with Large Language Models
Discover how large language models automate dynamic programming problem formulation, boosting efficiency in operations research and AI.
HiMA-Ecom: Advanced Training for Multi-Agent E-commerce AI
Discover HiMA-Ecom, a benchmark for joint training of hierarchical multi-agent AI assistants in e-commerce, boosting efficiency with HiMA-R1 method.