Solving an agent's repeated decisions once lifts an open model from 29% to 96%
Bellman language models treat an agent's recurring choices as a planning problem. The method reads past conversations into a fixed set of states, solves the best move for each once, and runs that as a controller around the model; unseen states go back to the LLM. On a telecom support benchmark, Qwen3.8-27B rose from 29% to 96% with 93% fewer model calls. It helps little where the hard part is writing content, such as fixing SymPy issues.