[
    {
        "id": "osp-22833",
        "type": "article-journal",
        "title": "Grounding Memory Summarization in Utility Intent",
        "author": [
            {
                "family": "Lei",
                "given": "Zhenyu"
            },
            {
                "family": "Shi",
                "given": "Mingjia"
            },
            {
                "family": "Fu",
                "given": "Xingbo"
            },
            {
                "family": "He",
                "given": "Haoyu"
            },
            {
                "family": "Wang",
                "given": "Qi R."
            },
            {
                "family": "Li",
                "given": "Jundong"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/grounding-memory-summarization-in-utility-intent",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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."
    }
]