feat(experimentalist): add Tau3 experimentalist workflow to docs - #999
Merged
Conversation
Contributor
Contributor
📝 WalkthroughWalkthroughThe PR documents an end-to-end τ-Bench optimization example, adds Tau3 Airline smoke dataset preparation and bounded Experimentalist settings, and propagates the configured or environment-provided model into the agent container. ChangesTau3 Airline smoke workflow
Sequence Diagram(s)sequenceDiagram
participant User
participant prepare-airline-smoke.sh
participant Experimentalist
participant Tau3 NOOA agent
User->>prepare-airline-smoke.sh: Prepare train and validation smoke datasets
prepare-airline-smoke.sh-->>User: Return dataset paths
User->>Experimentalist: Start bounded optimization run
Experimentalist->>Tau3 NOOA agent: Launch candidate with model environment
Tau3 NOOA agent-->>Experimentalist: Return evaluation results
Experimentalist-->>User: Write selected winner to run.json
Possibly related PRs
Suggested labels: Suggested reviewers: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In
`@plugins/nemo-experimentalist/examples/tau3-nooa-agent/prepare-airline-smoke.sh`:
- Around line 27-36: Update the dataset cache guard in prepare-airline-smoke.sh
to verify that every selected task in TRAIN_TASKS has its task.toml under
DATASET_ROOT before skipping the download. Redownload via the existing uv run
harbor download block whenever any of the five tasks is missing, while
preserving reuse only when all task files exist.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 6ed37ac1-9909-4a5c-9f06-347b3fe6b82d
📒 Files selected for processing (6)
docs/get-started/example-agent.mdxplugins/nemo-experimentalist/examples/tau3-nooa-agent/README.mdplugins/nemo-experimentalist/examples/tau3-nooa-agent/experimentalist-smoke.yamlplugins/nemo-experimentalist/examples/tau3-nooa-agent/harbor_wrapper.pyplugins/nemo-experimentalist/examples/tau3-nooa-agent/prepare-airline-smoke.shplugins/nemo-experimentalist/tests/experimentalist/test_tau3_nooa_agent.py
Contributor
|
Provide a bounded official-dataset workflow that customers can run through the NeMo CLI while recording Platform traces. Signed-off-by: Nico Tonozzi <ntonozzi@nvidia.com>
nicot
force-pushed
the
tau3-experimentalist-cli-example/ntonozzi
branch
from
July 30, 2026 20:33
0045319 to
50dd92c
Compare
nicot
changed the title
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/get-started/example-agent.mdx`:
- Line 88: Correct the spelling in the agent performance sentence by changing
“evalaution” to “evaluation,” without altering the surrounding text.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 7c0cfd0c-e4c0-4629-b9f7-23447c0600dc
📒 Files selected for processing (4)
docs/get-started/example-agent.mdxplugins/nemo-experimentalist/examples/tau3-nooa-agent/experimentalist-smoke.yamlplugins/nemo-experimentalist/examples/tau3-nooa-agent/harbor_wrapper.pyplugins/nemo-experimentalist/examples/tau3-nooa-agent/prepare-airline-smoke.sh
aleckhoury
approved these changes
Jul 30, 2026
This was referenced Jul 31, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This is not a great UX yet -- my next step will be to go back and clean up the docs and remove tau2, but this is working for now and I want to let others test it out.
Summary by CodeRabbit
New Features
Bug Fixes