Tutorials
RuleMem: Active Rule Memory for Long-Term Conversational Agents
arXiv:2609.03915v1 Announce Type: new Abstract: Question answering agents in long-term conversations must reason over massive, temporally dispersed dialogue histories. However, existing memory mechani
arXiv:2609.03915v1 Announce Type: new 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 extit{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 extit{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).
Related
- TransMem: Transforming Hidden States into Memory for Large Language Models
- MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization
- EventWeave: A Dynamic Framework for Capturing Core and Supporting Events in Dialogue Systems
- MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
Source: arXiv cs.CL | 2026-09-04