Transferable Expertise for Autonomous Agents via Real-World Case-Based Learning

ArXi:2604.12717v1 Announce Type: new LLM-based autonomous agents perform well on general reasoning tasks but still struggle to reliably use task structure, key constraints, and prior experience in complex real-world settings. We propose a case-based learning framework that converts experience from past tasks into reusable knowledge assets, allowing agents to transfer prior case experience to new tasks and perform structured analysis.