RuleMem: Active Rule Memory for Long-Term Conversational Agents

2026-09-03

AI Summary

为解决长期对话中记忆机制的语义鸿沟和推理不可靠问题，提出RuleMem框架，通过从历史对话中归纳逻辑规则来主动指导证据检索与推理。

Abstract

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).

Problem

• long-term conversations
• memory mechanisms
• semantic gaps
• unreliable reasoning

Innovation

• RuleMem
• Horn Clauses
• Rule Perplexity Consistency (RPC)
• long-term conversations
• active rule memory