ParaTool: Shifting Tool Representations from Context to Parameters
📰 ArXiv cs.AI
arXiv:2605.29561v1 Announce Type: new Abstract: Tool calling extends large language models (LLMs) by enabling grounded interaction with external executable interfaces, thereby supporting environment-coupled problem solving. However, mainstream in-context learning (ICL) approaches typically incorporate detailed tool documentation and usage examples directly into the context. This results in substantial inference overhead and heightened risks of hallucination as the context length grows. Conversel
Full Article
Title: ParaTool: Shifting Tool Representations from Context to Parameters
Abstract:
arXiv:2605.29561v1 Announce Type: new Abstract: Tool calling extends large language models (LLMs) by enabling grounded interaction with external executable interfaces, thereby supporting environment-coupled problem solving. However, mainstream in-context learning (ICL) approaches typically incorporate detailed tool documentation and usage examples directly into the context. This results in substantial inference overhead and heightened risks of hallucination as the context length grows. Conversel
Abstract:
arXiv:2605.29561v1 Announce Type: new Abstract: Tool calling extends large language models (LLMs) by enabling grounded interaction with external executable interfaces, thereby supporting environment-coupled problem solving. However, mainstream in-context learning (ICL) approaches typically incorporate detailed tool documentation and usage examples directly into the context. This results in substantial inference overhead and heightened risks of hallucination as the context length grows. Conversel
DeepCamp AI