{"id":"2609.25237","title":"Trains but Doesn't Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers","url":"https://codeofpaper.com/paper/2609.25237","arxiv_url":"https://arxiv.org/abs/2609.25237","published":"2026-09-21","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":3}