Agents pick each action before acting: Turn-BoN lifts terminal-task pass rates by 5–10% and halves the turns
Long-horizon agents execute one action per turn, sampled from a stochastic policy, so the same task sometimes succeeds and sometimes fails. Turn-BoN has a generator model propose several candidate actions at each turn and an off-the-shelf open-weight LLM selector choose one before the environment executes it. On Terminal-Bench v2.1 terminal tasks with Qwen3.6-35B and K2-Horizon-375B as generators, mean pass@1 rises by 5–10%, consistency across repeated attempts improves, and solving a task takes about 40–50% fewer turns than the baseline, at roughly 3–6 times the baseline's total tokens per trajectory.