view article Article Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic ibm-research • about 7 hours ago • 58
view article Article ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM ibm-research • 5 days ago • 13
MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments Paper • 2605.09131 • Published 24 days ago • 57