LiteExec: Scaling Down the Executor in Long-Horizon Agents

Long-horizon tasks involve different capability requirements, from high-level planning and task decomposition to direct execution and tool interaction. Monolithic agents apply a single model throughout, potentially misallocating model capacity and increasing inference costs. In this work, we investigate whether these differences can be exploited by pairing a large-model planner with a smaller executor. With this role separation, we find that scaling down model size for the executor under a large-model planner leads to a smaller performance drop than scaling down a monolithic agent, suggesting that execution is more amenable to scaling down. Additionally, the planner consumes less than $4\%$ of total tokens, leaving most token usage to smaller executors. However, off-the-shelf executors remain limited in performance and token efficiency due to ineffective collaboration with the planner. To address these limitations, we propose Executor GRPO, a simple yet effective reinforcement learning approach that trains a small executor using end-to-end task rewards with a frozen planner. The resulting model, LiteExec, exhibits emergent collaborative behaviors during training, including more informative feedback and more frequent reporting of execution difficulties. Experimental results demonstrate that pairing large-model planners with LiteExec improves performance and substantially reduces estimated inference costs relative to off-the-shelf executors, with improvements generalizing across planners and from coding to search tasks. Compared with the corresponding monolithic large-model agents, large-model planners paired with LiteExec-9B achieve competitive scores of $70.0$ (vs. $73.0$) on SWE-bench Verified and $76.0$ (vs. $78.7$) on SWE-bench Multilingual, while reducing large-model token usage by approximately $88\%$ and $90\%$ and estimated total inference costs by $24\%$ and $71\%$, respectively.