面向准确高效角色AI的认知启发情景记忆架构
Cognitively-Inspired Episodic Memory Architectures for Accurate and Efficient Character AI
AI总结：
针对现有角色AI方案存在的回复质量与延迟的权衡问题，提出认知启发的结构化情景记忆架构，实现高效准确的历史人物对话，还可支持传记分析可视化，适配资源受限场景。
摘要：
大语言模型在对话系统中扮演历史人物方面展现出潜力，但现有方案存在关键权衡：简单的检索增强生成会产生浅薄的回复，而多阶段反思虽能实现深度回复，却存在难以接受的高延迟。我们提出一种架构，通过离线数据增强和结构化情景记忆的高效并行检索解决这一矛盾。我们的系统将传记数据转换为1774条带有情感-语义元数据的增强第一人称记忆，随后采用两阶段检索，实现了0.52秒的提示生成速度。使用LLM-as-judge和RAGAs指标的评估显示，我们的方法在GPT-4上与传统RAG性能相当，同时在较小模型（GPT-3.5、GPT-3）上显著优于传统RAG，表明其对资源受限的部署场景具有特殊价值。除对话外，结构化记忆还支持新型可视化工具：时空热力图、情感轨迹分析和交互路径追踪，使该系统既可用作对话接口，也可作为传记分析的研究工具。我们以梵高作为测试案例，但该架构可推广至任何拥有大量文本记录的历史人物，为需要兼顾准确性与效率的教育、博物馆及研究应用提供了实用框架。
英文摘要：
Large language models show promise for embodying historical characters in dialogue systems, but existing approaches face a critical trade-off: simple retrieval-augmented generation produces shallow responses, while multi-stage reflection achieves depth at prohibitive latency. We present an architecture that resolves this tension through offline data augmentation and efficient parallel retrieval from structured episodic memory. Our system transforms biographical data into 1,774 enriched first-person memories with affective-semantic metadata, then employs two-stage retrieval achieving 0.52s prompt generation. Evaluation using LLM-as-judge and RAGAs metrics shows our approach achieves parity with traditional RAG on GPT-4 while significantly outperforming it on smaller models (GPT-3.5, GPT-3), suggesting particular value for resource-constrained deployments. Beyond dialogue, the structured memory enables novel visualization tools: spatiotemporal heatmaps, emotional trajectory analysis, and interactive path tracking, positioning the system as both a dialogue interface and research tool for biographical analysis. We use Van Gogh as a test case, but the architecture is generalizable to any historical figure with substantial textual records, offering a practical framework for educational, museum, and research applications requiring both accuracy and efficiency
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
