Grounding Memory Summarization in Utility Intent

2026-09-27

AI Summary

This study addresses the misalignment between memory summarization objectives and the preservation of evidence for future queries by proposing MemSuit, a self-distillation framework. MemSuit introduces a utility-oriented self-distillation mechanism wherein a teacher model generates utility-aware entries that a student model reconstructs from raw conversations, while the embedding model is fine-tuned to align with the retriever. Furthermore, by decomposing multifaceted independent units, the framework effectively prevents evidence erasure caused by single-query conditions. Integrating contrastive learning with retrieval-augmented generation, MemSuit consistently outperforms state-of-the-art baselines across diverse conversational query types. These results validate the effectiveness of evaluating memory value based on downstream utility.

Abstract

Existing summarizers for memory systems are typically optimized for human-facing criteria such as faithfulness, which misaligns with their true objective: preserving the evidence needed to support future queries. We show that conditioning summarization on query-answer pairs substantially improves answer quality, and that this utility-aware behavior is transferable across queries. Motivated by these findings, we propose MemSuit, a self-distillation framework in which a teacher summarizer, conditioned on observed query-answer pairs, produces utility-aware memory entries that a student learns to reproduce from the raw conversation alone. To prevent collateral erasure where conditioning on a single query-answer pair discards evidence relevant to other plausible queries, the teacher decomposes each block into multiple self-contained entries that preserve distinct query-relevant facets as independently retrievable units. To align the retriever with the compact, fact-dense style of teacher entries, we further fine-tune the embedding model with a contrastive objective supervised by teacher entries. Across a diverse suite of conversational query types, MemSuit consistently outperforms state-of-the-art baselines, confirming the value of grounding memory in downstream utility.

Problem

• Memory Summarization
• Utility Intent
• Conversational Memory
• Evidence Preservation

Innovation

• Self-distillation
• Utility-aware summarization
• Memory systems
• Collateral erasure prevention
• Contrastive fine-tuning