Latest AI/ML News
435 articles · 🧠 Research
arXiv:2608.13572v1 Announce Type: cross Abstract: We present The Architect, a system that turns Microsoft Excel into an interactive view of deep learn…
arXiv:2608.13571v1 Announce Type: cross Abstract: When a language model fails to answer a query on the first attempt, an agentic system retries, consu…
arXiv:2608.13570v1 Announce Type: cross Abstract: Latent reasoning has emerged as a powerful alternative to text-based Chain-of-Thought (CoT), offerin…
arXiv:2608.13568v1 Announce Type: cross Abstract: Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal…
arXiv:2608.13566v1 Announce Type: cross Abstract: Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchm…
arXiv:2608.13563v1 Announce Type: cross Abstract: Early-stage teams often lack users, time, and budget to run repeated UX studies, yet still need deci…
arXiv:2608.14528v1 Announce Type: new Abstract: This study investigates the methodological and theoretical properties of session handover in applicati…
arXiv:2608.14522v1 Announce Type: new Abstract: As AI systems make more morally loaded decisions across society, one response has been moral preferenc…
arXiv:2608.14509v1 Announce Type: new Abstract: Systems that ask a language model to reach a conclusion from many sources usually concatenate them int…
arXiv:2608.14490v1 Announce Type: new Abstract: We present a Test-time World-model Inference (Twin) system, in which a frontier coding agent writes an…
arXiv:2608.14456v1 Announce Type: new Abstract: Short-horizon forecasting of fine particulate matter (PM2.5) remains difficult when observations from…
arXiv:2608.14452v1 Announce Type: new Abstract: Spreadsheets are widely used to organize, analyze, and manipulate semi-structured data, yet automated…
arXiv:2608.14446v1 Announce Type: new Abstract: In the current artificial intelligence-driven innovation era, the pace of knowledge growth is accelera…
arXiv:2608.14441v1 Announce Type: new Abstract: Self-evolving agents improve future behavior from interaction experience, yet existing evaluations typ…
arXiv:2608.14426v1 Announce Type: new Abstract: AI is increasingly being used to help with AI R&D. Under certain conditions this feedback loop might b…
arXiv:2608.14425v1 Announce Type: new Abstract: LLM evaluations often use fixed sampling budgets, testing every item the same number of times even aft…
arXiv:2608.14407v1 Announce Type: new Abstract: We present a survey of the past and future of AI Scientists: machines capable of automating science. A…
arXiv:2608.14397v1 Announce Type: new Abstract: Zahavy [2026] argues that Large Language Models, despite their capabilities in induction and deduction…
arXiv:2608.14392v1 Announce Type: new Abstract: Neuron- and path-level interventions offer the finest-grained route to defending large language models…
arXiv:2608.14380v1 Announce Type: new Abstract: Many real-world tasks require LLM agents to interact with their environments over long execution horiz…