Skip to content

ReasoningAgent interim execution #1419

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 15 commits into from
Mar 20, 2025

Conversation

giorgossideris
Copy link
Collaborator

@giorgossideris giorgossideris commented Mar 19, 2025

Why are these changes needed?

Provide the option for interim execution of steps.

Related issue number

Closes #1418

Checks

@giorgossideris giorgossideris marked this pull request as draft March 19, 2025 12:20
@giorgossideris giorgossideris marked this pull request as ready for review March 19, 2025 15:38
@giorgossideris giorgossideris requested review from BabyCNM and Hk669 and removed request for BabyCNM March 19, 2025 15:38
@davorrunje
Copy link
Collaborator

Since Python 3.9, dict and tuple are the prefered way of annotating types. Please replace all Dict and Tuple with them.

@davorrunje davorrunje self-assigned this Mar 20, 2025
@giorgossideris
Copy link
Collaborator Author

thank you @davorrunje

@davorrunje davorrunje added this pull request to the merge queue Mar 20, 2025
Merged via the queue into ag2ai:main with commit 338f89b Mar 20, 2025
12 checks passed
Copy link

codecov bot commented Mar 20, 2025

Codecov Report

Attention: Patch coverage is 50.90909% with 27 lines in your changes missing coverage. Please review.

Files with missing lines Patch % Lines
...n/agents/experimental/reasoning/reasoning_agent.py 50.90% 24 Missing and 3 partials ⚠️
Files with missing lines Coverage Δ
...n/agents/experimental/reasoning/reasoning_agent.py 37.70% <50.90%> (+24.20%) ⬆️

... and 95 files with indirect coverage changes

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

marufaytekin pushed a commit that referenced this pull request Mar 23, 2025
* Align ReasoningAgent through prompting

* Introduce interim execution feature

* Change final prompt to create a better final response

* Interim execution fix for mcts

* Cleanup agents initialization

* Change multiple answers response prompt to be aligned with the other responding prompts

* Assert that executor has been initialized before executing node

* Update test for assertion error

* Update ReasoningAgent docs for interim_execution

* Not execute terminal nodes

* Fix precommit

* Fix tuple, dict typings

Co-authored-by: Davor Runje <[email protected]>

* Fix precommit

---------

Co-authored-by: Davor Runje <[email protected]>
Co-authored-by: Mark Sze <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[Feature Request]: ReasoningAgent Interim Execution of steps
3 participants