Topic - Edition
arXiv:2610.19068v1 Announce Type: cross Abstract: Tool-augmented LLM agents discover relevant APIs from large registries before planning execution, yet finite context windows prohibit injecting all tool definitions into…
arXiv:2604.18508v2 Announce Type: replace Abstract: Many recent document embedding models are trained on document-as-image representations, embedding rendered pages as images rather than the underlying source.…
arXiv:2604.06163v2 Announce Type: replace Abstract: Recent studies show that neural retrievers often exhibit source bias, ranking LLM-generated passages above semantically similar human-written ones, which threatens the…
arXiv:2610.20122v1 Announce Type: new Abstract: Large language models can reduce vocabulary mismatch in sparse retrieval by generating alternative views of a query. Once these views are searched independently, however,…
arXiv:2610.19528v1 Announce Type: cross Abstract: Retrieving external knowledge can improve large language model (LLM) translation by providing supplementary information such as idiom interpretations and terminology.…
arXiv:2512.07384v2 Announce Type: replace Abstract: In recommender systems, user-item interactions can be modeled as a bipartite graph, where user and item nodes are connected by undirected edges. This graph-based view…
arXiv:2607.13609v2 Announce Type: replace-cross Abstract: Recovering a latent potential from observed flow on a directed graph (a discrete Poisson problem with Dirichlet boundaries) is ill-posed, and the standard fix…
arXiv:2610.19578v1 Announce Type: new Abstract: Graph Collaborative Filtering models have achieved remarkable success in recommendation systems. However, they inherently suffer from a catastrophic representation…
arXiv:2610.08077v3 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction.…
arXiv:2609.18437v2 Announce Type: replace Abstract: In this work, we explore whether LLMs can predict and explain plausible materials for vehicle components such as brake discs or fuel injectors without extensive…
arXiv:2610.19608v1 Announce Type: new Abstract: Counts of which brands a large language model names are useful only if they hold long enough to act on. We test this with a pre-registered replication. The same 162…
arXiv:2606.26277v3 Announce Type: replace Abstract: Sequential user behavior modeling is widely adopted in industrial recommender systems; however, significant gaps remain in financial services, where pre-login web…
arXiv:2610.20048v1 Announce Type: new Abstract: Subject indexing assigns descriptors from a controlled vocabulary to bibliographic records, a task characterized by thousands of labels, few positive examples per label,…
arXiv:2610.20293v1 Announce Type: cross Abstract: Large language models increasingly generate multiple retrieval actions jointly, while downstream systems often provide only one reward for the resulting set.…
arXiv:2610.19065v1 Announce Type: new Abstract: Generative retrieval (GR) has emerged as a strong candidate generator for sequential recommendation as language models and semantic-item identifiers have improved.…
arXiv:2608.27394v4 Announce Type: replace-cross Abstract: Retrieved scientific literature can serve as inspiration for both human and AI scientists. Inspiration can take different forms: prior work may directly suggest…
arXiv:2610.20578v1 Announce Type: new Abstract: HPC users often download datasets on HPC systems for analysis and processing. When these datasets are comprised of hundreds of thousands (or more) of small files,…
arXiv:2609.25833v2 Announce Type: replace-cross Abstract: Automatic fact-checking poses a significant challenge in Arabic natural language processing due to the scarcity of datasets and resources. In this manuscript, we…
arXiv:2610.19398v1 Announce Type: new Abstract: Iterative retrieval-augmented generation (RAG) accumulates knowledge from retrieved evidence to answer complex questions, but existing methods struggle to reconstruct…
arXiv:2606.11350v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) degrades when applied to large, heterogeneous document collections. In RAG systems, dense similarity becomes less…
34 items available
