arXiv Artificial Intelligence

Learning to Retrieve Missing Evidence for Long-Term Memory QA

2 hours ago 30.09.2026 07:00 👁 2 views
Learning to Retrieve Missing Evidence for Long-Term Memory QA

Quick summary

arXiv:2609.37443v1 Announce Type: cross Abstract: Long-term memory enables language models to use past interactions in future conversations. However, evidence needed to answer a question may be scattered across distant turns, while the question itself omits clues needed to locate it. Retrieved facts can reveal these clues, motivating retrieval decisions conditioned on evidence already found. We introduce MERA (Missing-Evidence Retrieval Augmentation), which separates globally searchable memory from a question-specific evidence state. Verified evidence guides subsequent retrieval without restri

Key takeaways

  • arXiv:2609.37443v1 Announce Type: cross Abstract: Long-term memory enables language models to use past interactions in future conversations.
  • However, evidence needed to answer a question may be scattered across distant turns, while the question itself omits clues needed to locate it.
  • Retrieved facts can reveal these clues, motivating retrieval decisions conditioned on evidence already found.

Why it matters

The importance of “Learning to Retrieve Missing Evidence for Long-Term Memory QA” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗