Researchers proposed GeoSkill, an experience-driven hierarchical skill learning framework for geospatial agents, detailed in arXiv paper 2609.13667v1. GeoSkill combines a Hierarchical Skill Bank, spli…
Researchers introduced MACE, a Multi-Agent Candidate Event acquisition method that uses evidence-specialized LLM agents to refine event structure before linking, according to a new arXiv paper (arXiv:…
Researchers proposed a Position Encoding-Based Deformable Spatial Aggregation Module (PEBDSAM) that addresses over-smoothing, over-compression, fixed receptive fields, and topological noise in graph n…
A new arXiv survey (2609.13731v1) synthesizes 206 foundational studies and regulatory standards into a systems-security reference framework for trustworthy agentic AI, formalizing the general agent ar…
Researchers introduced JaxAHT, described as the first open-source, JAX-based library for the Ad Hoc Teamwork research lifecycle, achieving approximately 95x wall-clock speedup over PyTorch counterpart…
A new arXiv paper (arXiv:2609.13805v1) proposes an LLM-enhanced multi-agent reinforcement learning framework that simultaneously optimizes the grid, electric vehicles, and charging stations within a u…
Researchers presented SAILOR, a proof-of-concept system that detects unsupported numerical choices in natural-language optimization problems, asks users targeted follow-up questions, and updates the o…
Researchers introduced ClinAgent, a conversational agentic Retrieval-Augmented Generation (RAG) system built on a Large Language Model agent following the ReAct paradigm, which lets clinicians and res…
A reinforcement learning system called ViperQ, built on Auction Market Theory primitives, achieved +163.6% ROI on TSLA with a -27.5% max drawdown across 27,019 trades and +116.5% ROI on NVDA with a -4…
A new arXiv paper (arXiv:2609.13879v1) proposes a five-part attribution table for specifying how acquired representations enlarge a system's cognitive repertoire without transferring the capacities us…
A first-move retrieval module called Question's Gambit raised downstream agent answer accuracy from 83.1% to 90.5% with gpt-5.5 over the Pi-Serini agentic baseline on the BrowseComp-Plus benchmark, ac…
A new arXiv paper (2609.13995v1) argues that the debate over synthetic data in marketing research should shift from whether LLM-generated respondents work to when they work, distinguishing three types…
Researchers introduced UniCAR-RL, an annotation-free reinforcement learning framework that decouples perception and reasoning optimization in Multimodal Large Language Models (MLLMs) to improve comple…
Microsoft published a 38-page draft Humanist AI Code of Conduct on Monday and opened a public consultation to refine the guidelines, which it expects to apply to Microsoft AI (MAI) model development n…
Senate Majority Leader John Thune (R-S.D.) said Congress has a role in regulating AI and that "guardrails there make sense to me" for frontier models, putting him at odds with President Trump, who pos…
CrowdStrike CEO George Kurtz said slowing AI development will not eliminate the risks posed by the technology because potentially dangerous models are already widely available, telling CNBC that "the …
Contact center AI ROI is shifting from interaction volume to resolution quality and governed execution, according to Bob Laliberte, principal analyst for networking and observability at theCUBE Resear…
President Trump phoned Nvidia CEO Jensen Huang during the All-In Summit and called opposition to data centers a "hoax," according to CNBC Technology. Trump has also used his social media site to criti…
Insurers can move agentic AI from pilot to production at scale by relying on trusted data, human oversight, auditable workflows and controlled testing, according to a Forbes Innovation brand contribut…
Nvidia CEO Jensen Huang took a surprise onstage call from President Trump at the All-In Summit in Los Angeles on Monday, where Trump told Huang "the robots will not be taking over" and called warnings…