04:00
2026-09-23
arxiv.org
ai-agents
Trains but Doesn't Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers
A new arXiv paper (2609.25237v1) proposes a post-training delivery benchmark that tests whether LLM agents can be trusted as forward-deployed engineers (FDEs), rather than whether they can raise a met…