OpenWiki证据图改善智能体记忆
LangChain测试了作为智能体持久记忆层的OpenWiki，并在一项厂商实验中报告称，在需要跨多个来源回答的问题上，其准确率约为单独搜索的五倍。在维基引用之上加入证据图后，准确率又提高27%，引用一致性翻倍，每个正确答案的成本下降58%，但检索仍未完全确定。对于简单查询，不使用OpenWiki的搜索准确率相当且速度更快，而所报回答成本不含编译与维护费用。
实验表明，编译记忆与明确证据路径可帮助智能体进行重复的跨源推理，但收益取决于复用程度，且尚未获得独立验证。
Key Takeaways
- A compiled wiki gives agents domain context that retrieval alone must reconstruct. On questions spanning multiple sources, an agent using OpenWiki as a memory layer was 5x more accurate than one using grep tools alone.
- Adding an evidence graph helps agents follow the wiki back to supporting evidence. We turned citations and document references into explicit graph edges agents could follow. Compared with the wiki alone, this doubled how consistently the agent cited the same evidence, improved accuracy by 27%, and cut cost per correct answer by 58%.
- Save compiled memory for repeated cross-source reasoning. The wiki captures domain knowledge and complex relationships. Adding an evidence graph improves accuracy and retrieval consistency. For simple lookups, however, the agent without memory was just as accurate and faster.
Agents working across an organization’s policies, manuals, wikis, tickets, and code must navigate knowledge scattered across systems and teams. Finding a relevant passage is only the start. They also need to determine which rules apply, what has changed, and how one source affects another.
A persistent memory layer preserves knowledge and relationships for agents to reuse across tasks. Without it, agents often have to reconstruct that understanding on every question, making their work expensive and error-prone. This is especially challenging in banking and insurance, where policies and guidelines frequently amend or supersede one another.