Latest AI/ML News
8160 articles · arXiv cs.AI
arXiv:2610.04719v1 Announce Type: new Abstract: AI assistants receive requests that leave out information needed for a good outcome, for example about…
arXiv:2610.04699v1 Announce Type: new Abstract: A verifier for an agent faces rules of two kinds: the ones a fixed check can settle and the ones that…
arXiv:2610.04693v1 Announce Type: new Abstract: Agents are entering finance, healthcare and law, sectors where a violation leaves no lexical signature…
arXiv:2610.04691v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is typically evaluated under the implicit assumption that the und…
arXiv:2610.04686v1 Announce Type: new Abstract: Multi-agent debate can improve reasoning, yet often fails to beat simple majority voting. We argue tha…
arXiv:2610.04672v1 Announce Type: new Abstract: Large language models (LLMs) have progressively evolved into the core of autonomous agents. Building o…
arXiv:2610.04670v1 Announce Type: new Abstract: Fine-tuning a language model on new text degrades what it already does. Replay-free projectors such as…
arXiv:2610.04665v1 Announce Type: new Abstract: Linear radiation transport equations (RTEs) form the simulation foundations underpinning design and an…
arXiv:2610.04659v1 Announce Type: new Abstract: Vision-language-action (VLA) policies commonly learn action chunks through a fixed left-to-right (LTR)…
arXiv:2610.04646v1 Announce Type: new Abstract: Inference systems determine how fast and how cheaply language models can be served, so making them fas…
arXiv:2610.04635v1 Announce Type: new Abstract: Sparse attention reduces core-attention computation, but its indexers still incur repeated selection w…
arXiv:2610.04592v1 Announce Type: new Abstract: KRATOS is a group-structured bibliometric diagnostic that compares the distribution of documents (part…
arXiv:2610.04580v1 Announce Type: new Abstract: Multi-modal large language models (MLLMs) achieve strong modality understanding by pairing a large lan…
arXiv:2610.04561v1 Announce Type: new Abstract: Differentiable programming connects scientific computation with gradient-based inference, learning and…
arXiv:2610.04555v1 Announce Type: new Abstract: We propose $\mathrm{TRIZ}^{a}$ (TRIZ exponentiated by an agent), a general R\&D automation paradigm th…
arXiv:2610.04544v1 Announce Type: new Abstract: Many groups now delegate label ontology and metadata harmonization to agentic LLM pipelines. We built…
arXiv:2610.04542v1 Announce Type: new Abstract: Clinical LLMs must decide not only what diagnosis to produce, but also whether the available evidence…
arXiv:2610.04541v1 Announce Type: new Abstract: Purpose: To develop and evaluate an open-weight large language model (LLM) pipeline that converts an e…
arXiv:2610.04539v1 Announce Type: new Abstract: Latent world models learn to predict observed transitions, yet low prediction error alone does not gua…
arXiv:2610.04517v1 Announce Type: new Abstract: Deep time-series forecasting models have rapidly diversified, yet adapting them to a specific task sti…