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 restricting access to the global memory. We train a lightweight planner through reinforcement learning, rewarding queries that recover previously missing evidence. MERA achieves strong answer accuracy across Qwen3-30B and GPT-4o-mini backbones. With Qwen3-30B for evidence processing and answer generation, the trained 0.6B planner achieves 77.40% accuracy on LoCoMo and 71.29% on LongMemEval-S, exceeding a 30B planner without retrieval-grounded training by 4.10% and 3.96%, respectively. On LoCoMo, later retrieval rounds increase cumulative evidence recall from 55.5% to 80.5%.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Deng, Y. X., Zhang, Y., Liu, W., Xue, C., & Yang, S. (2026). Learning to Retrieve Missing Evidence for Long-Term Memory QA. https://omanscience.com/en/articles/learning-to-retrieve-missing-evidence-for-long-term-memory-qa
MLA 9
Deng, Yi-Xuan, et al. "Learning to Retrieve Missing Evidence for Long-Term Memory QA." https://omanscience.com/en/articles/learning-to-retrieve-missing-evidence-for-long-term-memory-qa.
Chicago (author–date)
Deng, Yi-Xuan, Yi Zhang, Wei Liu, Chao Xue, and Shuojin Yang. 2026. "Learning to Retrieve Missing Evidence for Long-Term Memory QA." https://omanscience.com/en/articles/learning-to-retrieve-missing-evidence-for-long-term-memory-qa.
Harvard
Deng, Y. X., Zhang, Y., Liu, W., Xue, C. and Yang, S. (2026) 'Learning to Retrieve Missing Evidence for Long-Term Memory QA', Available at: https://omanscience.com/en/articles/learning-to-retrieve-missing-evidence-for-long-term-memory-qa.
Vancouver
Deng YX, Zhang Y, Liu W, Xue C, Yang S. Learning to Retrieve Missing Evidence for Long-Term Memory QA. https://omanscience.com/en/articles/learning-to-retrieve-missing-evidence-for-long-term-memory-qa
IEEE
Y. X. Deng, Y. Zhang, W. Liu, C. Xue, and S. Yang, "Learning to Retrieve Missing Evidence for Long-Term Memory QA," https://omanscience.com/en/articles/learning-to-retrieve-missing-evidence-for-long-term-memory-qa.