arXiv:2608.13571v1 Announce Type: cross Abstract: When a language model fails to answer a query on the first attempt, an agentic system retries, consuming…
Category: AI
AI Used to Verify Toughest Mathematics Proof Yet
Representing a significant milestone in AI-assisted mathematical research, a team at Axiom Math has automatically verified the proof of a theorem relating…
The Architect: Interactive Visualization of Deep Learning Mathematics Directly in Microsoft Excel
arXiv:2608.13572v1 Announce Type: cross Abstract: We present The Architect, a system that turns Microsoft Excel into an interactive view of deep learning…
NVIDIA Guarantees up to $105B for 8-GW Ohio AI Campus Leased by OpenAI
NVIDIA has agreed to guarantee up to $105 billion in lease obligations at a planned 8-gigawatt AI data center campus in Pike County, Ohio, in a deal that…
Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study
arXiv:2608.13568v1 Announce Type: cross Abstract: Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal,…
Serve Robotics Brings Sidewalk Robot Delivery to Grubhub, Expands to Three New Cities
Serve Robotics and Grubhub have struck a partnership that puts Serve’s autonomous sidewalk robots on the Grubhub marketplace, starting in Chicago, Los…
Don’t Claim Benchmark-Oriented Optimization Improves General Coding Capability — Diverse Evaluation Is Required
arXiv:2608.13566v1 Announce Type: cross Abstract: Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks…
Split the Labor: Separating Evidence Interpretation from Decision Aggregation
arXiv:2608.14509v1 Announce Type: new Abstract: Systems that ask a language model to reach a conclusion from many sources usually concatenate them into…
Twin: Playing an Unknown Game with a Test-Time Digital Twin
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…
Participatory Moral AI Is Not Neutral: The Invisible Hand of Developers
arXiv:2608.14522v1 Announce Type: new Abstract: As AI systems make more morally loaded decisions across society, one response has been moral preference…