Repository navigation
docs(ai-red-teaming): honor explicit ATLAS objectives (no 1->N expansion) - #202
Merged
Merged
Conversation
…ne goal into many The agent reads generate_atlas_attack as a "campaign" and, given a single goal, enumerates several objectives of its own (or falls back to the bundled catalog) - so "run ATLAS with one objective" quietly becomes a multi-objective sweep. Add a one-line directive to pass exactly the user's objectives and scale total_budget accordingly, only broadening when the user asks for a sweep.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
When a user asks to run ATLAS with an explicit objective (or an exact count, e.g. "one objective"), the agent instead enumerates several objectives of its own or falls back to the bundled catalog. Root cause: the
generate_atlas_attacktool description frames ATLAS as a multi-objective "campaign" with no instruction to respect the caller's objective set.This adds a one-line directive: pass exactly the user's
objectives, scaletotal_budgetproportionally, and only broaden to multiple objectives / the catalog when the user asks for a sweep.Context
Test plan