Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search
This work addresses the problem of unstable training and inefficient reasoning in search agents for LLMs, representing an incremental improvement over existing RL methods.
The paper tackles the inefficiency and instability in RL-based search agents by proposing the HiExp framework, which transforms reasoning trajectories into hierarchical experience knowledge to regularize exploration, achieving substantial performance gains and strong generalization across benchmarks.
Reinforcement learning (RL) has become an effective approach for advancing the reasoning capabilities of large language models (LLMs) through the strategic integration of external search engines. However, current RL-based search agents often rely on a process of stochastic exploration guided by carefully crafted outcome rewards, leading to inefficient reasoning trajectories and unstable training. To address these issues, we propose a novel framework, Hierarchical Experience (HiExp), to enhance the performance and training stability of search agents. Specifically, we extract empirical knowledge through contrastive analysis and a multi-level clustering mechanism, transforming raw reasoning trajectories into hierarchical experience knowledge. By leveraging experience-aligned training, we effectively regularize stochastic exploration, evolving it into a strategic and experience-driven search process. Extensive evaluations on multiple complex agentic search and mathematical reasoning benchmarks demonstrate that our approach not only achieves substantial performance gains but also exhibits strong cross-task and cross-algorithm generalization.