mlsanityData to 14 Oct 2026

RuleMem: Active Rule Memory for Long-Term Conversational Agents

arXiv 2609.03915 ↗First posted 3 Sep 2026cs.CL cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

Question answering agents in long-term conversations must reason over massive, temporally dispersed dialogue histories. However, existing memory mechanisms primarily treat past information as textitpassively 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 textitactively 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 LongMemEvals*. 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).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 37 references that are in the map. First posted on arXiv 3 Sep 2026.

Builds on

20 of 37 references.

References · 20

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  5. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  6. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  7. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  8. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  9. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  10. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  11. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  12. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memorycited by 400
8 more
  1. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  2. 2025Memory in the Age of AI Agentscited by 303
  3. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 254
  4. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
  5. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 123
  6. 2025MemInsight: Autonomous Memory Augmentation for LLM Agentscited by 85
  7. 2024Towards Lifelong Dialogue Agents via Timeline-based Memory Managementcited by 51
  8. 2024CommunityKG-RAG: Leveraging Community Structures in Knowledge Graphs for Advanced Retrieval-Augmented Generation in Fact-Checkingcited by 11

Built on by

Not cited yet.