Google Research has introduced Retrieve-for-Train (R4T), a framework for search that returns coherent, diverse result sets. It trains a fan-out language…
Category: MarkTechPost
Google Releases Gemini 3.8 Live and 3.8 Live Extended Thinking for Production Grade Voice Agents
Google has released Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, its most advanced live dialogue models to date. The models execute tools and…
Nunchux AI Introduces VC-Attention: A Training-Free Low-Bit Attention Kernel That Speeds Up Video Diffusion Transformers
Nunchux AI has released VC-Attention, a training-free low-bit attention kernel built for video Diffusion Transformers (DiTs). It targets 2 problems at…
Stanford Researchers Release Paper2Agent: Turning Research Papers Into AI Agents That Reproduce Results and Run on New Data
Paper2Agent, published in Nature, converts papers into validated MCP tools, scoring 91.2% on 300 questions across 74 papers.
Knowledgator Releases GLiFormer: A 575M-Parameter Encoder That Hits 91.10 F1 on Nested JSON Extraction Without Generating Tokens
GLiFormer Large scores 91.10 F1 on nested JSON, near GPT-5.6-luna’s 91.96, while grounding every value in source spans.
Agent-net Open Sources Webagent: A Go Harness That Turns Any Website into a Guarded AI Agent
Agent-net, the team building an agent-to-agent marketplace where AI agents discover, trust, and pay each other, has released Webagent, an open source…
Meta Introduces ZGateway: A Stateless Proxy Tier That Unifies ZippyDB Traffic and Handles Over 1 Billion Operations Per Second
Meta engineering team introduced ZGateway, a proxy tier that now sits between client applications and ZippyDB, the Meta’s most widely used key value…
Sakana AI Researchers Introduce PC-ALM, a Layer-Local Alternative to Backpropagation That Trains 1000-Layer Networks
Sakana AI researchers Jeffrey Seely and Julian Gould introduce Augmented Lagrangian Predictive Coding (PC-ALM), a local-learning alternative to…
Reward AI Releases OM-1: A Robot Policy Trained on Human Demonstrations Only, With No Teleoperation or On-Robot Data
Reward AI has released OM-1 (Omnibody Model 1), a general-purpose manipulation policy trained entirely on human demonstrations captured with a 7-DoF…
Agent Harness vs Agent Framework vs MCP: Which Layer Owns the Loop, State, Tools, Permissions, and Recovery
A practitioner’s map of the 3 layers in a modern agent stack, with verified sources and an overlap analysis.