Get the latest tech news
The tool integration problem that’s holding back enterprise AI (and how CoTools solves it)
CoTools uses hidden states and in-context learning to enable LLMs to use more than 1,000 tools very efficiently.
CoTools offers a compelling alternative to existing methods by cleverly combining aspects of fine-tuning and semantic understanding while crucially keeping the core LLM “frozen”—meaning its original weights and powerful reasoning capabilities remain untouched. By separating the decision-making (Judge) and selection (Retriever) based on semantic understanding from the parameter filling (Calling via focused ICL), CoTools achieves efficiency even with massive toolsets while preserving the LLM’s core abilities and allowing flexible use of new tools. The framework’s reliance on semantic understanding via hidden states allows for nuanced and accurate tool selection, which could lead to more reliable AI assistants in tasks that require interaction with diverse information sources and systems.
Or read this on Venture Beat
