How to Train Your LLM Web Agent: A Statistical Diagnosis
Journal:
arXiv
Published Date:
Jul 5, 2025
Abstract
LLM-based web agents have recently made significant progress, but much of it
has occurred in closed-source systems, widening the gap with open-source
alternatives. Progress has been held back by two key challenges: first, a
narrow focus on single-step tasks that overlooks the complexity of multi-step
web interactions; and second, the high compute costs required to post-train
LLM-based web agents. To address this, we present the first statistically
grounded study on compute allocation for LLM web-agent post-training. Our
approach uses a two-stage pipeline, training a Llama 3.1 8B student to imitate
a Llama 3.3 70B teacher via supervised fine-tuning (SFT), followed by on-policy
reinforcement learning. We find this process highly sensitive to hyperparameter
choices, making exhaustive sweeps impractical. To spare others from expensive
trial-and-error, we sample 1,370 configurations and use bootstrapping to
estimate effective hyperparameters. Our results show that combining SFT with
on-policy RL consistently outperforms either approach alone on both WorkArena
and MiniWob++. Further, this strategy requires only 55% of the compute to match
the peak performance of pure SFT on MiniWob++, effectively pushing the
compute-performance Pareto frontier, and is the only strategy that can close
the gap with closed-source models.
