Advancing Tool-augmented Large Language Models: Integrating Insights From Errors In Inference Trees · The Large Language Model Bible Contribute to LLM-Bible

The Large Language Model Bible

Research on Large Language Models. Maintained by Sean Moran.

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

Advancing Tool-augmented Large Language Models: Integrating Insights From Errors In Inference Trees

Chen Sijia, Wang Yibo, Wu Yi-feng, Chen Qing-guo, Xu Zhao, Luo Weihua, Zhang Kaifu, Zhang Lijun. Arxiv 2024

[Paper]    
Agentic Efficiency And Optimization Fine Tuning Pretraining Methods RAG Reinforcement Learning Tools Training Techniques

Tool-augmented large language models (LLMs) leverage tools, often in the form of APIs, to enhance their reasoning capabilities on complex tasks, thus taking on the role of intelligent agents interacting with the real world. The recently introduced ToolLLaMA model by Qin et al. [2024] utilizes the depth-first search-based decision tree (DFSDT) method for reasoning with \(16000+\) real-world APIs, which effectively improves the planning and inferencing performance of tool-augmented LLMs compared to traditional chain reasoning approaches. However, their approach only employs successful paths from decision trees (also called inference trees) for supervised fine-tuning (SFT) during training, which does not fully exploit the advantages of the tree of thought. In this study, we propose an inference trajectory optimization framework based on the preference data extracted from decision trees to address this limitation. We first introduce a novel method for constructing preference data from the tree of thought, capitalizing on the failed explorations previously overlooked in the trees. Specifically, we generate an effective step-wise preference dataset, named ToolPreference, for tool use based on the ToolBench dataset. In the subsequent training phase, we first fine-tune the LLM with tool-usage expert trajectories and then use these step-wise preference pairs for direct preference optimization (DPO) to update the policy of the LLM, resulting in our ToolPrefer-LLaMA (TP-LLaMA) model. Our experiments demonstrate that by obtaining insights from errors in inference trees, TP-LLaMA significantly outperforms the baselines across almost all test scenarios by a large margin and exhibits better generalization capabilities with unseen APIs. At the same time, TP-LLaMA has also demonstrated superior reasoning efficiency compared to the baselines, making it more suitable for complex tool-usage reasoning tasks.

Similar Work