Autonomous LLM agents with human-out-of-loop

Posted by shishirpatil on Thursday April 11, 2024 @02:10PM
from the arxiv.org dept.

( 8 comments | 11 points | on HN )

Re:Autonomous LLM agents with human-out-of-loop by tianjunz on Thursday April 11, 2024 @02:41PM (#40005385)

Author of Gorilla Execution Engine (GoEx) here! The key idea behind GoEx: 1. "Post-facto validation" for assessing LLM actions after execution. 2. "Undo" button and “Damage confinement” abstractions to manage unintended actions & risks!

GoEx (code below) inherently supports Gmail/Slack/Dropbox/Spotify/Github, try it out to build your own LLM agents!

Blog: https://gorilla.cs.berkeley.edu/blogs/10_gorilla_exec_engine... Code: https://github.com/ShishirPatil/gorilla/tree/main/goex

[ Parent | on HN ]

Re:Autonomous LLM agents with human-out-of-loop by wonderer--2 on Thursday April 11, 2024 @04:02PM (#40006229)

Congratulations on the release! I have interests to integrate concepts of GoEX to my applications. What's some of the main focus for GoEX to improve, and make GoEx enterprise-grade and how far is the system away from getting there?

[ Parent | on HN ]

Re:Autonomous LLM agents with human-out-of-loop by Charlie-Ji on Thursday April 11, 2024 @03:38PM (#40005969)

Curious to see what are the common failure modes that the GoEX have, so that I can understand how the post-facto LLM validation has compared to those of pre-facto LLM validation

[ Parent | on HN ]

Re:Autonomous LLM agents with human-out-of-loop by polarbear-c on Thursday April 11, 2024 @04:08PM (#40006292)

Exciting work! Congrats! Hope to see a side-by-side comparison for LLM agent systems to see more clearly the advantages and limitation that GoEX offers.

[ Parent | on HN ]

Re:Autonomous LLM agents with human-out-of-loop by Charlie-Ji on Thursday April 11, 2024 @03:11PM (#40005701)

Very interesting to see GoEX the concept of “post-facto LLM validation," and concept of damage confinement, allowing reversible actions and limiting risk in real-world applications. Can't wait to try out the demos

[ Parent | on HN ]

Re:Autonomous LLM agents with human-out-of-loop by fanjiayan22 on Thursday April 11, 2024 @02:25PM (#40005222)

Exciting contributions to LLM tool uses; Can't wait to try it in Slack.

[ Parent | on HN ]

Re:Autonomous LLM agents with human-out-of-loop by oscillatingfans on Thursday April 11, 2024 @02:15PM (#40005109)

Excited to see what kind of agents can be built given an execution framework.

[ Parent | on HN ]

Re:Autonomous LLM agents with human-out-of-loop by sloth-d on Thursday April 11, 2024 @04:40PM (#40006583)

Congrats!! Such brilliant ideas and amazing work! Can't wait to see it being deployed in more applications. Also, second to what polarbear-c said, a side-by-side comparison with other LLM agent systems would be great!

[ Parent | on HN ]