Don't Adapt Small Language Models for Tools; Adapt Tool Schemas to the Models
Small language models (SLMs) enable scalable tool-augmented multi-agent systems where multiple SLMs handle subtasks orchestrated by a powerful coordinator. However, they struggle with tool-use tasks, particularly in selecting appropriate tools and identifying correct parameters. A common failure mode is \textit{schema misalignment}: models hallucinate plausible tool names that are absent from the provided tool schema, due to different naming conventions internalized during pretraining. Rather than training models to adapt to unfamiliar schemas, we propose adapting schemas to align with models' pretrained knowledge. We introduce \textbf{PA-Tool} (Pretraining-Aligned Tool Schema Generation), a training-free method that leverages peakedness, a signal used in contamination detection that indicates pretraining familiarity, to rename tool components. By generating multiple candidates and selecting the candidate with the highest peakedness, PA-Tool identifies pretraining-aligned naming patterns. Experiments on MetaTool and RoTBench show improvements of up to 17\%, with schema misalignment errors reduced by 80\%. PA-Tool enables small models to substantially improve tool-use accuracy without retraining, showing that schema-level interventions can unlock the tool-use potential of resource-efficient models. Our code is available at https://github.com/holi-lab/PA-Tool.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Estimating 2D Keypoints of Surgical Tools Using Vision-Language Models with Low-Rank Adaptation
This paper presents a novel pipeline for 2D keypoint estima- tion of surgical tools by leveraging Vision Language Models (VLMs) fine- tuned using a low rank adjusting (LoRA) technique. Unlike traditional Convolutional Ne…
Keypoint DetectionPose EstimationLeveraging Foundation Models for Histological Grading in Cutaneous Squamous Cell Carcinoma using PathFMTools
Despite the promise of computational pathology foundation models, adapting them to specific clinical tasks remains challenging due to the complexity of whole-slide image (WSI) processing, the opacity of learned features,…
AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical sec…
Leveraging Language for Accelerated Learning of Tool Manipulation
Robust and generalized tool manipulation requires an understanding of the properties and affordances of different tools. We investigate whether linguistic information about a tool (e.g., its geometry, common uses) can he…
Meta-LearningLearning Evolving Tools for Large Language Models
Tool learning enables large language models (LLMs) to interact with external tools and APIs, greatly expanding the application scope of LLMs. However, due to the dynamic nature of external environments, these tools and A…