Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling

TL;DR

This paper introduces Recycling Search Experience (RSE), a novel test-time search strategy for large language models that recycles intermediate insights to improve efficiency and reasoning performance.

Contribution

RSE is a training-free, experience-guided approach that distills search trajectories into a shared bank, enabling positive and negative recycling to reduce redundant computations.

Findings

RSE outperforms strong baselines on multiple reasoning benchmarks.

Theoretically formalizes efficiency gains over independent sampling.

Achieves better compute-efficiency trade-offs in test-time scaling.

Abstract

Test-Time Scaling enhances the reasoning capabilities of Large Language Models by allocating additional inference compute to broaden the exploration of the solution space. However, existing search strategies typically treat rollouts as disposable samples, where valuable intermediate insights are effectively discarded after each trial. This wasted rollout-level experience leads to substantial computational redundancy, as models repeatedly re-derive discovered conclusions and revisit known dead ends across extensive attempts. To bridge this gap, we propose \textbf{Recycling Search Experience (RSE)}, a self-guided, training-free strategy that turns test-time search from a series of isolated trials into a cumulative, experience-guided process. By actively distilling raw trajectories into a shared experience bank, RSE enables positive recycling of intermediate conclusions to shortcut redundant derivations and negative recycling of failure patterns to prune encountered dead ends. Theoretically, we provide an analysis that formalizes the efficiency gains of RSE over independent sampling in solving complex reasoning tasks. Empirically, extensive experiments on HMMT24, HMMT25, IMO-Bench, and HLE show that RSE consistently outperforms strong baselines under comparable computational budgets, establishing a strong compute-efficiency frontier for test-time scaling.