用因果干预筛选记忆，让长时对话模型更准更稳。
Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents
- 通过因果干预评估记忆对回答的影响，选择真正有用的记忆。
- 在新构建的基准上，表现优于向量、摘要等传统方法。
- 适合需要可靠长期记忆的智能对话系统开发者。
长时程大语言模型代理依赖持久记忆来支持跨会话交互，但现有记忆系统多基于语义相似性或广义历史包含来检索，将所有记忆视为等效有用。这一假设脆弱，因记忆可能主题相关却无关、过时或误导。本文提出因果记忆干预（CMI），通过受控干预估计候选记忆对模型回答的影响，筛选出提升任务表现、抑制不稳、无关或有害记忆的上下文。为评估该设定，我们构建了因果标注的长对话基准Causal-LoCoMo，包含用户请求、结构化记忆库、有用记忆、无关干扰项及合成有害记忆。对比向量、图、反思、摘要、全历史和无记忆基线，结果表明CMI在回答质量与抗误导性之间取得更好平衡，说明可靠长时记忆需基于因果效用而非仅相关性进行选择。完整框架、基准构建代码与实验流程已开源。
原文摘要 · Abstract (English)
Long-horizon LLM agents rely on persistent memory to support interactions across sessions, yet existing memory systems often retrieve context using semantic similarity or broad history inclusion, treating retrieved memories as uniformly useful. This assumption is fragile because memories may be topically related while remaining irrelevant, stale, or misleading. We propose Causal Memory Intervention (CMI), a causal memory-selection technique that estimates how candidate memories affect the model's answer under controlled interventions, selecting memories that improve task performance while suppressing unstable, irrelevant, or harmful ones. To evaluate this setting, we introduce Causal-LoCoMo, a causally annotated benchmark derived from long conversational data, where each example contains a user request, a structured memory bank, useful memories, irrelevant distractors, and synthetic harmful memories. We compare CMI against vector, graph, reflection, summary, full-history, and no-memory baselines. Results show that CMI achieves a stronger balance between answer quality and robustness to misleading memory, suggesting that reliable long-term memory requires selecting context based on causal usefulness rather than relevance alone. The full framework, benchmark construction code, and experimental pipeline are available at https://github.com/Saksham4796/causal-memory-intervention.
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。