microsoft / microsoft/ExACT

Acknowledgment and credit for ExACT in independent agent framework (dda_scaffold)

Open
#10 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
52
Forks
18
PR merge metrics
No merged PRs in 30d

Description

Good afternoon ExACT research team.

I have cited your work in a research initiative I published, which is the culmination of about one year of efforts on my side developing an algorithm (the DDA ~ Dynamic Decision Algorithm) that is focused on persistent agent identity through psychological realism, combined with novel RAG and memory approaches.

While exploring projects in Azure Foundry, I discovered ExACT and found it an excellent foundation for adapting my theoretical DDA model—particularly its MCTS patterns, agentic structures, and search dynamics.

I hope that you will welcome the adaptions I have made, though it is not a fork of your code. I used my team of AI agents to learn your core methodologies and then apply them into my own scaffold. Nonetheless, I credit your team with the first acknowledgement in my project.

My project addresses a related but distinct question: enabling agents to maintain identity persistence without relying on chat logs, via an independent, externalized "mind."

I welcome any feedback, or simply your acceptance of this shared/derived work. I'm happy to modify attributions if you feel adjustments are needed.

Cheers, happy Chanukah, merry Christmas, happy new years and happy holidays overall

My project is found here:
https://github.com/snakewizardd/dda_scaffold

https://snakewizardd.github.io/dda_scaffold/

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No repository file, test, or entry point is identified in the issue; start by reviewing the repository and the linked DDA project to determine whether an attribution or documentation change is appropriate. Done would require a maintainer decision on the requested credit or feedback, followed by a clearly scoped documentation task if one is accepted.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
documentation
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.