CAVE-Mem: Boundary-Aware Experience Validation for Memory Search

arXiv:2610.00238v1 Announce Type: cross Abstract: Long-term memory agents increasingly rely on it- erative search and reusable experience to answer questions over large personal, factual, or narrative histories. However, current experience-memory systems largely optimize relevance: they re- trieve past search lessons that appear similar to the current state and inject them into the prompt. A relevant experience can still be harmful when the memory substrate, question intent, answer granularity, or evidence boundary changes. We propose CAVE- Mem, a training-free framework that represents experience as a typed intervention operator with applicability, boundary, and utility conditions. CAVE-Mem first obtains a base memory-search answer, then allows an operator to change it only if the oper- ator matches the current substrate, answer contract, evidence boundary, and cross-fitted utility; otherwise the system abstains. Experiments across long-term conversational memory, multi-hop question answering, and long-document narrative reasoning show consistent gains over relevance-only experience reuse.

Related

• Self-Correcting Long-Horizon Search Agents via Tree-Structured Memory
• Valhalla: A Layered Knowledge-State and Service-Governance Framework for Long-Term Scientific Knowledge Work
• MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agents
• TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory
• Learning to Retrieve Missing Evidence for Long-Term Memory QA

Source: arXiv cs.AI | 2026-10-02