SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.00467 · 2024

Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
kvadityasrivatsa/llm-routing canonical 1 of 1
FunctionStatusWhere it lives
get_label_list Ran kvadityasrivatsa/llm-routing/routing_classifiers/multi_label_classifier/llm_multiclassifier.py
code served (permissive licence) · get_code("9b8ff1213c52173e")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

With the rapid development of LLMs, it is natural to ask how to harness their capabilities efficiently. In this paper, we explore whether it is feasible to direct each input query to a single most suitable LLM. To this end, we propose LLM routing for challenging reasoning tasks. Our extensive experiments suggest that such routing shows promise but is not feasible in all scenarios, so more robust approaches should be investigated to fill this gap.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2405.00467")
get_code_for_paper("2405.00467")
have("2405.00467")

Connect an agent — have() is free.