Introducing AFlow: Automating Agentic Workflow Generation by MetaGPT https://
arxiv.org/abs/2410.10762 https://
github.com/geekan/MetaGPT
/tree/main/examples/aflow
…
AGENTS
-
AFlow: Automating Agentic Workflow Generation by MetaGPT
By
–
-
Future Autonomous Systems Will Outpace Manual Control Defense
By
–
When you get autonomous you will laugh that you tried to defend manual.
-
Google AI Studio vs ChatGPT: Mobile and Voice Usability Comparison
By
–
You mean https://
aistudio.google.com/prompts/new_ch
at
… ? Not for mobile use. ChatGPT is way better there. At least when using voice, which I often do -
Grok vs ChatGPT: Performance Comparison on Practical Tasks
By
–
Just found one thing Grok fails on that ChatGPT answers properly. We rented a manual transmission Opal in Spain. I tried many things and couldn’t figure out how to put it in reverse. ChatGPT’s first suggestion was right. Grok didn’t even suggest it. Do you have others? Oh
-
WebRL Self-Evolving Framework Boosts Open LLM Web Agents
By
–
8). WebRL – proposes a self-evolving online curriculum RL framework to bridge the gap between open and proprietary LLM-based web agents; it improves the success rate of Llama-3.1-8B from 4.8% to 42.4%, and from 6.1% to 43% for GLM4-9B; the open models significantly surpass the
-
Vision-Language Agents Vulnerable to Pop-up Adversarial Attacks
By
–
5). Attacking Vision-Language Agents via Pop-ups – shows that integrating adversarial pop-ups into existing agent testing environments leads to an attack success rate of 86%; this decreases the agents' task success rate by 47%.
-
HfApiEngine improvement simplifies open-LLM agent creation
By
–
A nice PR from @BruleNaudet in transformers.agents just improved HfApiEngine. This makes the creation of open-LLM-powered agents even easier with our free Inference API!
-
Autogen-based agent team tops GAIA benchmark submissions
By
–
It's not a new framework, it's simply a team of agent based on Microsoft's autogen framework! And submissions of this structure from Microsoft have long been near the top of the GAIA benchmark.
-
Hoping to see Dec’s live video interpretation; compute cost near $50/hr
By
–
Hoping to see the live video interpretation by Dec. They went silent on that after the demo. Guessing the compute cost is far greater than advanced voice mode ($18/hr), probably close to $50/hr.