Hint use agent #316
Merged
Hint use agent #316
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
… into generic_agent_hinter
Hints retrieval in generic agent
Refactor Hint Retrieval
* Make LLM retreival topic index selection more robust
#310) * add new flag to skip hints with the current goal in the hint source traces
* rename generic_agent_hinter to hint_use_agent for clarity * Add deprecation warning and module alias for generic_agent_hinter * improve module aliasing for submodules * Add todo rename agent name * black * bugfix: check for hint_db only when use_task_hint is true. * fix: address missing initialization and correct args reference in choose_hints method * black
* address comments * format
* add env variable for ray port * document env variables
hnekoeiq
reviewed
Nov 20, 2025
| hint_index_type: str = "sparse" | ||
| hint_query_type: str = "direct" | ||
| hint_index_path: str = "indexes/servicenow-docs-bm25" | ||
| hint_retriever_path: str = "google/embeddinggemma-300m" |
Collaborator
There was a problem hiding this comment.
I think this is missing some params such as hint_retrieval_model, hint_level, hint db path.
hnekoeiq
reviewed
Nov 26, 2025
| @@ -0,0 +1,19 @@ | |||
| import importlib, sys, warnings | |||
|
|
|||
| OLD = __name__ | |||
Collaborator
There was a problem hiding this comment.
@amanjaiswal73892 We can remove generic_agent_hinter files from this PR, no?
Collaborator
Author
There was a problem hiding this comment.
It's a temporary alias of hint_use_agent for backward compatibility. Some existing pickled traces may still use the old namespace.
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Outdated suggestions cannot be applied.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.
This pull request introduces a new "hint use agent" implementation for AgentLab, refactors the generic agent hinter module, and adds scripts for running generic and hinter agents. The changes improve agent modularity, configuration flexibility, and documentation, while also updating environment variable documentation. The most important changes are grouped below.
Added Hint-Use Agent
GenericAgentimplementation insrc/agentlab/agents/hint_use_agent/generic_agent.py, featuring modular hint retrieval (docs, sparse/dense, database), agent configuration, and robust error handling. This agent is designed to be the baseline for ServiceNow papers and supports various hinting modes.src/agentlab/agents/generic_agent_hinter/__init__.pyto alias its submodules to the newhint_use_agentmodule and warn about the upcoming deprecation, improving code organization and forward compatibility.src/agentlab/agents/hint_use_agent/__init__.pythat exposes agent configurations and the new agent class, consolidating the baseline agent API.Experiment scripts
experiments/generic/run_generic_agent.pyandexperiments/generic/run_generic_agent.shfor launching generic agents with configurable benchmarks, LLMs, and parallelization options. [1] [2]experiments/hinter/run_hinter_agent.pyandexperiments/hinter/run_hinter_agent.shfor running hinter agents with flexible hinting parameters and parallelization, supporting both debug and relaunch modes. [1] [2]Documentation and configuration
README.mdto fix theOPENAI_API_KEYtypo and document new Ray dashboard environment variables, improving setup clarity for users.