让对话记忆主动推理，提升长对话问答准确率。
RuleMem: Active Rule Memory for Long-Term Conversational Agents
- 从对话中自动提炼可复用的逻辑规则，主动指导记忆检索与推理。
- 在LoCoMo数据集上比平均基线高27.47分，相对提升54.3%。
- 适合需要长期记忆与逻辑推理的智能对话系统开发者。
长期对话中的问答代理需对大量、时间分散的对话历史进行推理。然而，现有记忆机制主要将过去信息视为被动存储的事实，导致语义断层和不可靠推理。为解决这一问题，我们提出RuleMem，一种基于规则的记忆框架，从历史交互中诱导可复用的逻辑规则，主动引导证据检索与推理。具体而言，RuleMem从对话中构建自然语言形式的命题逻辑（Horn clauses），并通过规则困惑度一致性（RPC）机制进行验证。这些生成的规则不仅能检索语义相距较远的证据，还为答案生成提供明确逻辑结构。我们在两个长期对话基准测试集LoCoMo和LongMemEval_s*上对RuleMem进行了全面评估。在包含14个基线的严格对比中，RuleMem在LoCoMo上达到最高准确率，超过基线平均分27.47点（相对提升54.3%）。
原文摘要 · Abstract (English)
Question answering agents in long-term conversations must reason over massive, temporally dispersed dialogue histories. However, existing memory mechanisms primarily treat past information as \textit{passively} stored facts, leading to semantic gaps and unreliable reasoning. To address this limitation, we propose RuleMem, a rule-based memory framework that induces reusable logical rules from historical interactions to \textit{actively} guide both evidence retrieval and reasoning. Specifically, RuleMem constructs natural-language Horn clauses from conversations and validates them via a Rule Perplexity Consistency (RPC) mechanism. These induced rules enable the retrieval of semantically distant evidence while providing an explicit logical structure for answer generation. We conducted a comprehensive evaluation of RuleMem on two long-term conversational benchmarks, LoCoMo and LongMemEval_s*. In a rigorous comparison against 14 baselines on LoCoMo, RuleMem achieved the highest accuracy, exceeding the baseline average by 27.47 points (a 54.3% relative improvement).
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。