arXiv:2608.23848v1 Announce Type: new Abstract: Budget-constrained agentic search arises when an LLM agent must refine candidates under a small evaluation…
Category: AI
Lancium and NVIDIA Partner to Deploy Gigawatt-Scale AI Factories
Lancium, the Texas energy-infrastructure company behind the Abilene campus that anchors the Stargate buildout, has signed a strategic collaboration with…
Granite.Trust Policy Tools: Shareable, Actionable Policies for Generative AI Applications
arXiv:2608.23870v1 Announce Type: new Abstract: When it comes to safety policies for generative AI, one size does not fit all. Each organization and use…
Oana Jinga, Co-Founder, Chief Commercial and Product Officer of Dexory – Interview Series
Oana Jinga, Co-Founder, Chief Commercial and Product Officer of Dexory, is an experienced technology and commercial leader with a background spanning…
In-Context Inpainting for Time Series Forecasting
arXiv:2608.23855v1 Announce Type: new Abstract: We propose ICI-Time, a novel framework that reframes time series forecasting as a visual inpainting task,…
Do LLMs Understand Limit Order Book Dynamics?
arXiv:2608.23706v1 Announce Type: new Abstract: A large language model (LLM) trained on synthetic limit order book (LOB) data achieves near perfect scores…
Generating Biomedical Fact-Checking Reports with RL-Enhanced Agentic Search
arXiv:2608.23811v1 Announce Type: new Abstract: Automated fact-checking is essential for ensuring the reliability of public health information, yet the…
AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
arXiv:2608.23740v1 Announce Type: new Abstract: Concurrent multi-agent coding promises division of labor across modules, robustness through redundancy,…
Agentic Resource Discovery (ARD): An open specification for agent discovery
AWS Agent Registry gives your organization a centralized, searchable catalog for agents, tools, and skills. It works with the open Agentic Resource…
Serving Masked Diffusion LLMs: Characterization and Design Principles from Real Hardware
arXiv:2608.23807v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) can in principle generate text faster than autoregressive (AR)…