Synthius-Mem: 基于大脑启发的hallucination抵抗性人格记忆实现94.4%的记忆准确率和99.6%的对抗鲁棒性于LoCoMo
Synthius-Mem: Brain-Inspired Hallucination-Resistant Persona Memory Achieving 94.4% Memory Accuracy and 99.6% Adversarial Robustness on LoCoMo
AI总结：
Synthius-Mem通过结构化人格记忆系统在LoCoMo基准上实现94.4%的记忆准确率和99.6%的对抗鲁棒性，优于现有系统并超越人类表现。
摘要：
为AI代理提供可靠且不产生幻觉的长期记忆仍是一个开放性问题。当前针对LLM代理的记忆方法--滑动窗口、摘要、基于嵌入的RAG和扁平事实提取--每种方法都减少了token成本但引入了灾难性信息丢失、语义漂移或对用户未披露事实的不可控幻觉。根本原因在于架构：在LoCoMo基准上发表的每种记忆系统都将对话视为对原始或轻度摘要对话片段的检索问题，且没有报告对抗鲁棒性，即拒绝回答用户从未披露的事实的能力。我们提出了Synthius-Mem，一种受大脑启发的结构化人格记忆系统，采用根本不同的方法。与检索所说内容不同，Synthius-Mem提取关于人物的已知内容：一个完整的个性提取管道将对话分解为六个认知领域（生物信息、经历、偏好、社交圈、工作、心理测量），在每个领域内整合和去重，并通过CategoryRAG检索结构化事实，延迟为21.79毫秒。在LoCoMo基准（ACL 2024，10个对话，1,813个问题）上，Synthius-Mem实现了94.37%的准确率，超过了所有已发表的系统，包括MemMachine（91.69%，对抗得分未报告）和人类表现（87.9 F1）。核心记忆事实准确率达到98.64%。对抗鲁棒性，即没有竞争对手系统报告的幻觉抵抗度量，达到99.55%。Synthius-Mem相比完整上下文回放减少了约5倍的token消耗，同时实现了更高的准确性。Synthius-Mem在LoCoMo上实现了最先进的结果，并且据我们所知，是唯一一个既超过人类水平表现又报告对抗鲁棒性的个性记忆系统。
英文摘要：
Providing AI agents with reliable long-term memory that does not hallucinate remains an open problem. Current approaches to memory for LLM agents -- sliding windows, summarization, embedding-based RAG, and flat fact extraction -- each reduce token cost but introduce catastrophic information loss, semantic drift, or uncontrolled hallucination about the user. The structural reason is architectural: every published memory system on the LoCoMo benchmark treats conversation as a retrieval problem over raw or lightly summarized dialogue segments, and none reports adversarial robustness, the ability to refuse questions about facts the user never disclosed. We present Synthius-Mem, a brain-inspired structured persona memory system that takes a fundamentally different approach. Instead of retrieving what was said, Synthius-Mem extracts what is known about the person: a full persona extraction pipeline decomposes conversations into six cognitive domains (biography, experiences, preferences, social circle, work, psychometrics), consolidates and deduplicates per domain, and retrieves structured facts via CategoryRAG at 21.79 ms latency. On the LoCoMo benchmark (ACL 2024, 10 conversations, 1,813 questions), Synthius-Mem achieves 94.37% accuracy, exceeding all published systems including MemMachine (91.69%, adversarial score is not reported) and human performance (87.9 F1). Core memory fact accuracy reaches 98.64%. Adversarial robustness, the hallucination resistance metric that no competing system reports, reaches 99.55%. Synthius-Mem reduces token consumption by ~5x compared to full-context replay while achieving higher accuracy. Synthius-Mem achieves state-of-the-art results on LoCoMo and is, to our knowledge, the only persona memory system that both exceeds human-level performance and reports adversarial robustness.
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。
