EviBack通过约束证据的教师回退，让AI搜索代理在无反馈时也能学习有效搜索。
EviBack: Search-Agent Reinforcement Learning via Evidence-Constrained Teacher Backoff
- 用证据约束的教师回退机制，为无反馈搜索组提供辅助监督信号。
- 在7个开放域问答基准上，相比Search-R1提升多跳和单跳宏F1。
- 适合构建更鲁棒的智能搜索代理，尤其在缺乏即时反馈场景下。
强化学习使代理式RAG系统能够从可验证的结果奖励中学习多轮搜索，但全零轨迹组缺乏比较信号，可能掩盖有用搜索行为。我们提出EviBack，一种基于证据约束的教师回退机制，在保留可验证动作奖励的同时，为这些组提供辅助监督。该方法将证据评估与答案精炼分离，防止参考答案覆盖证据不足判断。一个全自动端到端的GPT-5.5辅助APE流程，从人工编写的单提示双任务教师出发，自动划分并标注轨迹数据，完成消融实验、任务分解、评估与选择，生成门控的两阶段教师。相比人工设计，新教师在下游任务中提升了F1值与有效答案率，同时减少搜索次数、重复查询和强制终止。在七个开放域问答基准及三个Qwen3模型规模上，EviBack优于Search-R1，显著提升单跳与多跳宏F1。
原文摘要 · Abstract (English)
Reinforcement learning enables Agentic RAG systems to learn multi-turn search from verifiable outcome rewards, but all- zero rollout groups provide no comparative signal and may hide useful search behavior. We present EviBack, an evidence- constrained Teacher backoff that supplies auxiliary super- vision to such groups while preserving verifiable Actor re- wards. It separates evidence assessment from answer refine- ment, preventing reference answers from overriding evidence- insufficiency judgments. A fully automated, end-to-end GPT- 5.5-assisted APE pipeline starts from a manually authored single-prompt dual-task Teacher, automatically partitions and labels rollout data, and performs ablation, task decomposition, evaluation, and selection to produce a gated two-stage Teacher. Compared with the manual design, the resulting Teacher im- proves downstream F1 and valid-answer rate while reduc- ing search, duplicate queries, and forced termination. Across seven open-domain QA benchmarks and three Qwen3 scales, EviBack improves F1 over Search-R1 and raises both single- and multi-hop macro F1. We guarantee that the code will be made publicly available at a later stage.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。