[rollout] feat: pass all dataset fields to agent loop run #2810
+22
−21
Conversation
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
wuxibin89
requested review from
eric-haibin-lin and
zhaochenyang20
as code owners
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request refactors the agent loop to accept arbitrary dataset fields via **kwargs, which improves flexibility. However, the implementations in ReactAgentLoop, SingleTurnAgentLoop, and ToolAgentLoop now unsafely access kwargs["raw_prompt"]. This will cause a KeyError if the dataset is not configured to provide this field. I've added critical comments with suggestions to handle this case gracefully by checking for the key's existence before access.
Collaborator
|
@PopSoda2002 could help to review! thanks so much! |
docs/advance/agent_loop.rst
Outdated
| AgentLoopOutput: Agent loop output. | ||
| """ | ||
| raise NotImplementedError | ||
| @abstractmethod |
Collaborator
There was a problem hiding this comment.
Is there a format issue? There seems to be an additional space
5 tasks
Contributor
will take a look later 🛫 |
vermouth1992
approved these changes
Jul 30, 2025
yellowbee686
pushed a commit
to yellowbee686/verl
that referenced
this pull request
Jul 31, 2025
…#2810) ### What does this PR do? Pass all dataset fields from `RLHFDataset` to agent loop run, including: - raw_prompt - tools_kwargs - multi_modal_data - ...
Juniper1021
pushed a commit
to Juniper1021/verl
that referenced
this pull request
Aug 7, 2025
…#2810) ### What does this PR do? Pass all dataset fields from `RLHFDataset` to agent loop run, including: - raw_prompt - tools_kwargs - multi_modal_data - ...
whatadayG
pushed a commit
to whatadayG/verl
that referenced
this pull request
Sep 5, 2025
…#2810) ### What does this PR do? Pass all dataset fields from `RLHFDataset` to agent loop run, including: - raw_prompt - tools_kwargs - multi_modal_data - ...
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
What does this PR do?
Pass all dataset fields from
RLHFDatasetto agent loop run, including: