On Turn-Level Best-of-N Sampling for Scaling LLM Agents

In this work, we evaluate a simple inference-time scaling approach based on turn-level best-of-N sampling () for large language model (LLM) agents on complex, long-horizon tasks. We instantiate this using a generator-selector framework with two LLMs; at each turn, a generator model generates N candidate actions and a selector model selects one of them, which is then executed in the environment. This paper is closely related to the work of {zainullina2025guided} who used critic models for guided search at inference time. Different from their work, we evaluate if off-the-shelf, open-weight LLMs can be effective at comparing different candidate actions directly. Experiments on long-horizon terminal tasks show that can lead to significant performance improvements, both in terms of accuracy (5--10%) and consistency across repeated attempts. Analysis of agent trajectories reveal a shift in agent behaviour towards desirable patterns such as reduction in number of attempts to solve the task, improved task instruction following, debugging and testing.