Skip to content

Conversation

@nikivanstein
Copy link
Contributor

Motivation

  • Add documentation surface for the AlphaEvolve benchmark instances used in the project so users can discover and run them easily.
  • Surface both the runnable reference scripts and the programmatic benchmark definitions in the project README and Sphinx docs.

Description

  • Added an AlphaEvolve Benchmarks section to README.md that links the runnable scripts in run_benchmarks/ and the packaged benchmark definitions under iohblade/benchmarks.
  • Added a new Sphinx page docs/benchmarks.rst that summarizes the benchmark domains and points users to task READMEs and sources.
  • Updated docs/index.rst to include the new benchmarks page in the Sphinx toctree so the page appears in the documentation.

Testing

  • No automated tests or linters were run because this change only modifies documentation files and adds a new docs page.

Codex Task

@nikivanstein nikivanstein merged commit e806157 into feature/mcts-lhns-fixes Jan 20, 2026
0 of 6 checks passed
nikivanstein added a commit that referenced this pull request Jan 21, 2026
* Added Multi LLM and experiment for diversity start

* Fixing Claude connector

* fixing ioh dependency

* Fixing sync issues due to pickling the same file in multiple threads

* improved error messages

* Cleaning error messages

* Nice errors!

* fixing tokencost

* New experimental setups

* setting up full experiment

* fixing issues in exp

* working setup

* Added math import

* Added debug mode for easy testing of end to end stuff

* ioh

* Last version

* Setting up first experiment for guided llm mutation

* feedback and error handling in blade was broken..

* lock update

* black

* Added additional plotting options for CEG

* Added additional experiments

* Solving Photonics issues

* Resolving mcts errors

* Resolved issues with MCTS and cleaned up experiments

* Better generalized plotting functions and new ablation studies.

* added visualisation mabbob guided

* Added operator colloring.

* Updated visualisations

* small changes

* Added hlp problem class

* hlp problem runner

* implemented run for rule driven

* added rules

* added hlp problem

* HLP experiment ready

* Small changes for visualisations in paper.

* Small changes

* removed

* Added statistical test functions.

* cleaning up

* clearning up notebooks

* clearning up notebooks

* clearning up notebooks

* Cleaning up plotting code

* Removing specific ref for LLaMEA

* Add HLP tests and document AUC utilities (#91)

* black

* remove circular

* Add AlphaEvolve benchmark documentation (#92)

* Fixed tests

* black

* black

* for now remove hlp

* remove generated problems
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants