Sep 2026· Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing· Vol abs/2609.33417· 0 citations· 37 references
Computer Science
TL;DR
This work proposes 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, confirming the value of grounding memory in 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.
This work proposes a novel training-free method that generates a very large number of queries with minimal LLM usage by compositionally combining a small set of atomic components and applies LLM reasoning to construct a high-quality document set that balances precision and recall while capturing the user's core intent.
Yunah Jang, Kang-il Lee, Joongbo Shin et al.· Conference on Empirical Meth...· 0 citations
The results show that explicitly selecting and integrating evidence improves long-context reasoning while enabling more compact generation, and the strongest overall result among the evaluated open-source models is obtained.
This work introduces DocHop, a benchmark for integrated chart--context reasoning in document-style images and constructs DocHop via a stochastic logic-first generation pipeline with controllable reasoning depth and visual density, to enable systematic evaluation.
Zhuo-Ran Yu, Le Thien Phuc Nguyen, Jaden Park et al.· 1 citation
This work introduces AgenticInterleave, a single-agent ReAct framework for retrieval-supported answer generation, together with IVR-12, a 12-dimensional rubric for assessing the content, presentation, and image quality of interleaved references and model outputs, and evaluates both short-answer correctness and interlea...
Large language models (LLMs) are increas- ingly deployed as long-horizon conversational agents, motivating growing interest in mem- ory systems. However, existing benchmarks primarily evaluate memory through QA-style probing rather than in-situ conversational usage. We introduce LOCOMO-CONV, a conversa- tional memory b...
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.