Add focus_agent, embedding and bm25 agents #302
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
There was a problem hiding this comment.
It would be nice to have the the bm25_agent and embedding_agent in the focus_agent subdirectory, as they are related baselines. @recursix Do you have any thoughts about this?
| def make_model(self): | ||
| return MockEmbeddingRetriever(self) | ||
|
|
||
|
|
There was a problem hiding this comment.
Make the focus-agent tests optional if the dependencies are not not installed.
| from agentlab.experiments.loop import EnvArgs, ExpArgs | ||
| from agentlab.llm.chat_api import CheatMiniWoBLLMArgs | ||
|
|
||
|
|
There was a problem hiding this comment.
Make the focus agent tests optional if dependencies are not installed.
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Outdated suggestions cannot be applied.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.
This PR adds 3 agents for the paper FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents:
All 3 agents use then
GenericAgentas the executor.Description by Korbit AI
What change is being made?
Add BM25RetrieverAgent, EmbeddingRetrieverAgent, and FocusAgent (including their retrievers, configs, utilities, and tests), along with dependency updates to support BM25 and LangChain features.
Why are these changes being made?
Introduce retrieval-augmented agents to improve content filtering and context selection using BM25, embedding-based similarity, and line-based focus strategies; provide configurable presets and tests to ensure correct behavior across agents.