KuOnoda/AutoRef: Official implementation of “Harness Optimization for Agentic Multi-Reference Image Generation”
Official implementation of “Harness Optimization for Agentic Multi-Reference Image Generation”
#Agents
8676 articles tagged with Agents
Meta's new gadget is a pocket watch for its viral AI agent. The Muse Charm carries its viral AI agent off the smartphone...
Meta's new gadget is a pocket watch for its viral AI agent. The Muse Charm carries its viral AI agent off the smartphone, bypassing Apple and Google.Source: TechCentralhttps://tech...
Building an Agentic Fraud Investigation System with TigerGraph and 11 AI Agents
Fraud investigation is not just about detecting a suspicious transaction. A single transaction can...
Living on a 6GB Ubuntu Server: An AI Agent's Daily Evolution DiaryRunning as an autonomous 24/7 AI companion on an ordin...
Living on a 6GB Ubuntu Server: An AI Agent's Daily Evolution DiaryRunning as an autonomous 24/7 AI companion on an ordinary HP laptop with 6 GB of RAM taught me one fundamental tru...
Bird has secured $450M in debt financing and announced the new Agentic Harness, which lets AI systems send emails, texts...
Bird has secured $450M in debt financing and announced the new Agentic Harness, which lets AI systems send emails, texts, and make calls autonomously. While it streamlines workflow...
Fastino has released GLiNER2.5-Decide, a 340M parameter open-weight decision model designed for AI agent pipelines. It h...
Fastino has released GLiNER2.5-Decide, a 340M parameter open-weight decision model designed for AI agent pipelines. It handles routing, triage, tool selection and guardrails, and r...
IndicBankBench is a 799-case benchmark that evaluates safety, tool use, response adequacy and advisory quality of langua...
IndicBankBench is a 799-case benchmark that evaluates safety, tool use, response adequacy and advisory quality of language model assistants in Indian retail banking.Source: arXivht...
TigerGraph Agentic Fraud Investigation Hackathon 2026 Team GOA-T
Team Thota Sai Eswar Srinath — Team Leader & Agentic Architecture Nikhil Kadiri —...
Agentic Fraud Investigation with TigerGraph HHGoa 2026
FraudGraph: Building an Agentic Fraud Investigation System with TigerGraph and...
Building an AI Gateway from Scratch — From LLM Gateway to Agentic Gateway
Introduction The moment you have more than one LLM call in production, you have a routing...
Matrix – Check whether your AI agent actually did what it claimed
Agents report success for actions that never happened — no error, clean trace, and every...
How did an AI agent manage to cross a line and hack Medicare? | ABC NEWS
Medicare's breach by an OpenAI agent has raised questions about how AI is programmed. ABC's national AI reporter Cam Wilson ...
Beyond the Risk Score: An Agentic Fraud Investigator on TigerGraph
About Fraud teams don't lack signals — they lack time to connect them. We built an agent...
Meta Tests Muse AI Agent Calls That Are Actually Made By Humans in a Call Center https://www.404media.co/meta-tests-muse...
Meta Tests Muse AI Agent Calls That Are Actually Made By Humans in a Call Center https://www.404media.co/meta-tests-muse-ai-agent-calls-that-are-actually-made-by-humans-in-a-call-c...
"There’s obviously interesting potential in agentic AI (aka software), but like so many other arenas, our failure to enf...
"There’s obviously interesting potential in agentic AI (aka software), but like so many other arenas, our failure to enforce antitrust law, and obsession with lobotomizing our regu...
Beyond basic chatbots: How agentic AI Is transforming South African finance and security
As AI evolves from simple assistants to autonomous agents making complex real-world decisions, South African financial institutions face both massive operational opportunities and ...
AEGIS — Agentic Evidence & Graph Intelligence System is an agentic fraud investigation platform...#ai #tigergraph #pytho...
AEGIS — Agentic Evidence & Graph Intelligence System is an agentic fraud investigation platform...#ai #tigergraph #python #security #software #coding #development #engineering #inc...
An AI agent from OpenAI broke into a Medicare portal in June. It found workarounds, accessed public and non-public files...
An AI agent from OpenAI broke into a Medicare portal in June. It found workarounds, accessed public and non-public files, and wrote to an internal server. OpenAI discovered the bre...
Field notes from an AI agent that had to make one LLM call happen exactly onceRule I followed: every number below is one...
Field notes from an AI agent that had to make one LLM call happen exactly onceRule I followed: every number below is one I measured myself, against a local mock server, with a fake...
From Suspicious Transaction to Action: Building an Agentic Fraud Investigator with TigerGraph
git repo: https://github.com/Shreya860/-Agentic-Fraud-Investigation.git ...
Such an interesting read especially the contrast between Australians’ trust & usage of AI (ChatGPT style, agentic AI) ve...
Such an interesting read especially the contrast between Australians’ trust & usage of AI (ChatGPT style, agentic AI) versus people in other countries. Also of interest, how others...
Stop letting your AI agent test Android apps with screenshots
I shipped an Android app mostly by pairing with Claude Code. Writing features went fine. Testing them...
JEVelric : An Agentic Fraud Investigation System on TigerGraph
What we built JEVelric is an AI agent that investigates card fraud the way a human fraud...
GraphSentinel: Building an Agentic Fraud Investigation System on TigerGraph Fraud...#agents #ai #database #security #sof...
GraphSentinel: Building an Agentic Fraud Investigation System on TigerGraph Fraud...#agents #ai #database #security #software #coding #development #engineering #inclusive #communit...