无需标签和模型更新，智能代理通过搜索外部证据自优化映射。
Mapping Smarter, Not Harder: A Test-Time Reinforcement Learning Agent That Improves Without Labels or Model Updates
- 测试时用强化学习动态优化字段映射，自动识别模糊匹配。
- 100轮迭代后准确率从56.4%提升至93.94%，低置信度映射减少85%。
- 适合缺乏文档的工业场景，可解释性强，无需重训练。
企业智能平台需整合来自多个第三方厂商的日志以完成下游任务，但测试时厂商文档常缺失、错位、格式混乱或不完整，导致模式映射困难。本文提出一种无需标注数据或模型权重更新的强化学习代理，在推理阶段：1）识别模糊的字段映射；2）生成针对性网络搜索查询获取外部证据；3）基于置信度奖励机制迭代优化映射。以Microsoft Defender for Endpoint日志转换为通用模式为例，该方法将映射准确率从纯LLM的56.4%提升至RAG的72.73%，最终在100次迭代后达93.94%（使用GPT-4o）。同时，低置信度映射数量减少85%。该方法提供了一种基于证据、透明可解释的解决方案，为未来产业问题提供了更鲁棒、可问责、可扩展、高效、灵活、适应性强且可协作的新路径。
原文摘要 · Abstract (English)
The Enterprise Intelligence Platform must integrate logs from numerous third-party vendors in order to perform various downstream tasks. However, vendor documentation is often unavailable at test time. It is either misplaced, mismatched, poorly formatted, or incomplete, which makes schema mapping challenging. We introduce a reinforcement learning agent that can self-improve without labeled examples or model weight updates. During inference, the agent: 1) Identifies ambiguous field-mapping attempts. 2) Generates targeted web-search queries to gather external evidence. 3) Applies a confidence-based reward to iteratively refine its mappings. To demonstrate this concept, we converted Microsoft Defender for Endpoint logs into a common schema. Our method increased mapping accuracy from 56.4\%(LLM-only) to 72.73\%(RAG) to 93.94\% over 100 iterations using GPT-4o. At the same time, it reduced the number of low-confidence mappings requiring expert review by 85\%. This new approach provides an evidence-driven, transparent method for solving future industry problems, paving the way for more robust, accountable, scalable, efficient, flexible, adaptable, and collaborative solutions.
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。