基于因果干预的记忆选择用于长时域大语言模型智能体
Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents
AI总结：
本文提出Causal Memory Intervention（CMI）方法，通过因果推理选择大语言模型的长期记忆，以提高回答质量和鲁棒性，同时引入Causal-LoCoMo基准数据集进行评估。
摘要：
长时域大语言模型智能体依赖持久记忆来支持跨会话的交互，但现有记忆系统通常使用语义相似性或广泛历史包含来检索上下文，将检索到的记忆视为统一有用。这一假设是脆弱的，因为记忆可能在主题上相关，但仍然无关、过时或误导性。我们提出了Causal Memory Intervention（CMI），一种因果记忆选择技术，通过在受控干预下估计候选记忆如何影响模型的答案，选择提高任务性能的同时抑制不稳定、无关或有害的记忆。为了评估这一设置，我们引入了Causal-LoCoMo，一个从长对话数据中衍生出的因果标注基准，其中每个示例包含用户请求、结构化记忆库、有用的记忆、无关干扰项以及合成有害记忆。我们比较了CMI与向量、图、反思、摘要、完整历史和无记忆基线。结果表明，CMI在回答质量和对误导性记忆的鲁棒性之间实现了更强的平衡，表明可靠的长期记忆需要基于因果有用性而非相关性本身来选择上下文。完整的框架、基准构建代码和实验流程可在https://github.com/Saksham4796/causal-memory-intervention获取。
英文摘要：
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.
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。
