The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The paper introduces LOCOMO-CONV, a conversational memory benchmark that expands on the existing LoCoMo dataset with four query styles—dialog, implicit, counterfactual, and composed—designed to evaluate memory systems in realistic conversational settings. Experiments across five memory systems reveal that conversational framing uncovers significant retrieval gaps missed by traditional QA benchmarks, particularly for implicit and composed queries, and that strong retrieval does not necessarily translate into higher response quality. The study also highlights silent grounding in implicit queries, where memory enhances contextual grounding without explicitly presenting the gold fact, suggesting a need for reasoning-based memory elaboration.
arXiv:2605. 12213v2 Announce Type: replace Abstract: LLM-based conversational AI agents struggle to maintain coherent behavior over long horizons due to limited context.
arXiv:2609.07093v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enables large language models (LLMs) to answer questions by accessing external knowledge and has been widely a...
The paper introduces T$^2$Mem, a Test-Time Memory construction framework that defers memory building to inference, allowing large language models to adaptively retrieve and organize episode-level metadata and raw interactions during reasoning. By extracting lightweight metadata offline and progressively constructing query-specific memory at test time, T$^2$Mem reduces overhead and improves performance on long-horizon tasks. Experiments on LoCoMo and LongMemEval demonstrate consistent gains over strong baselines across various backbone LLMs.
arXiv:2603. 00026v2 Announce Type: replace-cross Abstract: Memory management is essential for LLM agents in long-term interactions.
UTILMEM is a new diagnostic benchmark that tests how conversational agents use long‑term memory, focusing on reasoning over dense histories, spotting implicitly relevant memories, synthesizing distributed evidence, and resisting interference from similar distractors. It contains 1,717 instances across five domains and evaluates a range of retrieval‑based and memory‑augmented systems. The study shows that strong performance on traditional factual recall does not guarantee effective memory utilization, highlighting a gap between retrieving information and integrating it into coherent, task‑oriented outputs.