Papers
arxiv:2402.15506

AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning

Published on Feb 23
· Submitted by akhaliq on Feb 26
Authors:
,
,
,
,
,

Abstract

Autonomous agents powered by large language models (LLMs) have garnered significant research attention. However, fully harnessing the potential of LLMs for agent-based tasks presents inherent challenges due to the heterogeneous nature of diverse data sources featuring multi-turn trajectories. In this paper, we introduce AgentOhana as a comprehensive solution to address these challenges. AgentOhana aggregates agent trajectories from distinct environments, spanning a wide array of scenarios. It meticulously standardizes and unifies these trajectories into a consistent format, streamlining the creation of a generic data loader optimized for agent training. Leveraging the data unification, our training pipeline maintains equilibrium across different data sources and preserves independent randomness across devices during dataset partitioning and model training. Additionally, we present xLAM-v0.1, a large action model tailored for AI agents, which demonstrates exceptional performance across various benchmarks.

Community

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Paper author

Nice paper! Thanks for the insights.

Did you also compare two versions of xLAM, one trained with your standard format, and one just with various formats? I am curious on how much performance gain we got from standardizing the tool usage trajectories.

Sign up or log in to comment

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2402.15506 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2402.15506 in a Space README.md to link it from this page.

Collections including this paper 4