LightSearcher: Efficient DeepSearch via Experiential Memory

TL;DR

LightSearcher is an RL-based framework that uses experiential memory and adaptive rewards to optimize search tool usage, significantly improving efficiency while maintaining accuracy in deep reasoning tasks.

Contribution

It introduces a novel RL framework with experiential memory and contrastive reasoning, balancing accuracy and efficiency in DeepSearch systems.

Findings

Reduces search tool calls by 39.6%

Cuts inference time by 48.6%

Maintains state-of-the-art accuracy

Abstract

DeepSearch paradigms have become a core enabler for deep reasoning models, allowing them to invoke external search tools to access up-to-date, domain-specific knowledge beyond parametric boundaries, thereby enhancing the depth and factual reliability of reasoning. Building upon this foundation, recent advances in reinforcement learning (RL) have further empowered models to autonomously and strategically control search tool usage, optimizing when and how to query external knowledge sources. Yet, these RL-driven DeepSearch systems often reveal a see-saw trade-off between accuracy and efficiency-frequent tool invocations can improve factual correctness but lead to unnecessary computational overhead and diminished efficiency. To address this challenge, we propose LightSearcher, an efficient RL framework that incorporates textual experiential memory by learning contrastive reasoning trajectories to generate interpretable summaries of successful reasoning patterns. In addition, it employs an adaptive reward shaping mechanism that penalizes redundant tool calls only in correct-answer scenarios. This design effectively balances the inherent accuracy-efficiency trade-off in DeepSearch paradigms. Experiments on four multi-hop QA benchmarks show that LightSearcher maintains accuracy comparable to SOTA baseline ReSearch, while reducing search tool invocations by 39.6%, inference time by 48.6%, and token consumption by 21.2%, demonstrating its superior efficiency.