MGRetrieval grounds reflective retrieval in historical memory structure for long-term dialogue, yielding 8.91% F1 and 11.11% BLEU-1 gains over baselines on LoCoMo with Qwen models.
InProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 25972–25981
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agents
MGRetrieval grounds reflective retrieval in historical memory structure for long-term dialogue, yielding 8.91% F1 and 11.11% BLEU-1 gains over baselines on LoCoMo with Qwen models.