arXiv:2605. 06142v2 Announce Type: replace-cross Abstract: When people recount personal memories, they often refer to people, places, and events indirectly, relying on con-textual cues rather than explicit names.
arXiv:2609.38155v1 Announce Type: cross Abstract: Answering questions about long videos often requires connecting events involving the same objects across hours or days. Chronological descriptions an...
arXiv:2607. 19359v1 Announce Type: new Abstract: Long-term memory is essential for LLM agents that interact across sessions, yet current memory benchmarks primarily evaluate single-hop recall, leaving multi-hop association largely unmeasured.
arXiv:2605. 28969v2 Announce Type: replace-cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user.
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...
arXiv:2608.23507v1 Announce Type: cross Abstract: Historical people may appear under different languages, scripts, and transcription traditions, while distinct individuals may share highly similar or...
The paper presents a detailed examination of narrative elements—agency, setting, and events—within the Dolma web-scale pretraining corpus. Using a framework of 11 interpretable dimensions, the authors hand‑annotated 400 passages, expanded this to a 25,000‑passage LLM‑labeled dataset, and trained NarraBERT models to predict narrative features across 13 million passages, producing the NarraDolma dataset. The study reveals that narrative structure is measurable at scale and that narrative qualities vary unevenly across different data sources, topics, and formats, highlighting gaps in current data curation practices.
arXiv:2607. 05577v1 Announce Type: new Abstract: Long-form fiction writers need memory that answers multi-hop questions about evolving story state: who knows a secret and when they learned it, whether an event preceded the narration that revealed it, whether a setup paid off, and how a relationship shifted.
arXiv:2608. 03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history.
BioELX is a retrieve‑rerank framework for cross‑lingual biomedical entity linking that tackles two key problems: the English‑biased UMLS alias training data and the degradation caused by naïvely adding context. It fine‑tunes SapBERT_multi with Wikidata‑derived cross‑lingual alias supervision to create shared concept neighborhoods, and then reranks candidates using pretrained LLMs with mention‑anchored prompting to focus on the target mention. Experiments demonstrate state‑of‑the‑art performance on four benchmarks, improving Recall@1 by 4.8–18.2 percentage points without task‑specific annotations.
arXiv:2609.26780v1 Announce Type: cross Abstract: Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distingu...
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.
The paper introduces a benchmark for recommending SNOMED CT concepts from masked clinical contexts, using data from the SNOMED CT Entity Linking Challenge v1.2.1 derived from MIMIC-IV-Note. It evaluates several methods—including a popularity baseline, sparse TF‑IDF prototypes, dense embeddings, and retrieval‑augmented hybrids—finding that sparse TF‑IDF achieves the best performance with Recall@1 of 14.81% and Recall@10 of 33.43%. The study highlights that concept frequency and lexical context strongly influence recommendation quality, with many test pairs involving concepts unseen during training.