让AI记忆可追溯、可审计，提升长期任务表现
Eywa: Provenance-Grounded Long-Term Memory for AI Agents
- 记忆按证据-事实-上下文分层存储，确保每步可追溯
- 在多个基准上达90%以上准确率，支持复杂长时任务
- 适合需要高可靠性与可解释性的智能体开发场景
能跨会话持续运行的AI代理需要可检索、可审计、可更新和可擦除的记忆系统。现有系统常将源证据、提取的事实、检索的上下文与回答策略混为单一不可见的提示路径，导致错误难以诊断：错误答案可能源于证据缺失、提取不支持、状态过期、检索失败或模型行为偏差。我们提出Eywa，一种以证据为先的可溯源记忆架构。Eywa在推导出标准事实前先存储不可变的源证据，通过类型化信号和源支持验证提取的记忆，并通过无大模型调用的确定性多路径读取机制返回有限上下文。检索到的上下文与回答指令分离，使同一记忆底座可在前沿、预算和本地模型上评估。在冻结的、记录生成物的检索配置下，Eywa在LoCoMo C1-C4数据集上以Claude Sonnet 4.6完成写入与问答角色，达到90.19%判断准确率；在LongMemEval-S上达88.2%检索充分性准确率；在包含700个问题的技术记忆压力测试集BEAM上，平均关键信息得分81.45%，通过率≥0.5的得分达85.29%。所有完整问题级产物（含问题、真值答案、模型答案、检索上下文、标签）已公开于https://eywa.to/research。
原文摘要 · Abstract (English)
AI agents that persist across sessions need memory they can retrieve, audit, update, and erase. Existing memory systems often collapse source evidence, extracted facts, retrieved context, and answer policy into one opaque prompt path, making failures difficult to diagnose: a wrong answer may come from missing evidence, unsupported extraction, stale state, retrieval loss, or answer-model behavior. We present Eywa, a provenance-grounded memory architecture built around evidence before belief. Eywa stores immutable source evidence before deriving canonical facts, validates extracted memories against typed signals and source support, and retrieves bounded memory context through a deterministic multi-route read path with zero LLM calls inside retrieval. Retrieved context is returned separately from answer instructions, allowing the same memory substrate to be evaluated across frontier, budget, and local answer models. Under a frozen, artifact-recorded retrieval configuration, Eywa reaches 90.19% judge accuracy on the LoCoMo C1-C4 split with Claude Sonnet 4.6 write and QA roles. On LongMemEval-S, it reaches 88.2% retrieval-sufficiency accuracy. On BEAM, a 700-question technical-memory stress benchmark, it reaches 81.45% mean nugget score and 85.29% pass@score >= 0.5. Full per-question artifacts, including questions, gold answers, model answers, retrieved context, and labels, are published at https://eywa.to/research.
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。