Jiafu Wu

Jian Li, Yizhang Jin, Dongqi Liu et al.

Retrieval augmented generation (RAG) reduces hallucinations and factual errors in large language models (LLMs) by conditioning generation on retrieved external knowledge. Recent search agents further cast RAG as an autonomous, multi-turn information-seeking process. However, existing methods often accumulate irrelevant or noisy documents and rely on sparse reinforcement learning signals. We propose \textbf{S}elf-\textbf{E}volving \textbf{Search}, a Self-Evolving Search agent that improves online search behavior through three components, memory purification, atomic query training, and dense rewards. SE-Search follows a \textit{Think-Search-Memorize} strategy that retains salient evidence while filtering irrelevant content. Atomic query training promotes shorter and more diverse queries, improving evidence acquisition. Dense rewards provide fine-grained feedback that speeds training. Experiments on single-hop and multi-hop question answering benchmarks show that \texttt{SE-Search-3B} outperforms strong baselines, yielding a $10.8$ point absolute improvement and a $33.8\%$ relative gain over Search-R1.\footnote{We will make the code and model weights publicly available upon acceptance.}

Jian Li, Dongsheng Chen, Zhenhua Xu et al.

Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools for a multi-turn information-seeking process autonomously. However, we identify a critical training instability that leads to catastrophic model collapse: Importance Sampling Distribution Drift(ISDD). In Group Relative Policy Optimization(GRPO), a widely adopted TARL algorithm, ISDD manifests as a precipitous decline in the importance sampling ratios, which nullifies gradient updates and triggers irreversible training failure. To address this, we propose \textbf{S}earch \textbf{A}gent \textbf{P}olicy \textbf{O}ptimization (\textbf{SAPO}), which stabilizes training via a conditional token-level KL constraint. Unlike hard clipping, which ignores distributional divergence, SAPO selectively penalizes the KL divergence between the current and old policies. Crucially, this penalty is applied only to positive tokens with low probabilities where the policy has shifted excessively, thereby preventing distribution drift while preserving gradient flow. Remarkably, SAPO requires only one-line code modification to standard GRPO, ensuring immediate deployability. Extensive experiments across seven QA benchmarks demonstrate that SAPO achieves \textbf{+10.6\% absolute improvement} (+31.5\% relative) over Search-R1, yielding consistent gains across varying model scales (1.5B, 14B) and families (Qwen, LLaMA).