AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
MP3•Episoder hjem
Manage episode 433992456 series 2954468
Innhold levert av Rob. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av Rob eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.
We introduce AnyTool, a large language model agent designed to revolutionize the utilization of a vast array of tools in addressing user queries. We utilize over 16,000 APIs from Rapid API, operating under the assumption that a subset of these APIs could potentially resolve the queries. AnyTool primarily incorporates three elements: an API retriever with a hierarchical structure, a solver aimed at resolving user queries using a selected set of API candidates, and a self-reflection mechanism, which re-activates AnyTool if the initial solution proves impracticable. AnyTool is powered by the function calling feature of GPT-4, eliminating the need for training external modules. We also revisit the evaluation protocol introduced by previous works and identify a limitation in this protocol that leads to an artificially high pass rate. By revising the evaluation protocol to better reflect practical application scenarios, we introduce an additional benchmark, termed AnyToolBench. Experiments across various datasets demonstrate the superiority of our AnyTool over strong baselines such as ToolLLM and a GPT-4 variant tailored for tool utilization. For instance, AnyTool outperforms ToolLLM by +35.4% in terms of average pass rate on ToolBench. Code will be available at https://github.com/dyabel/AnyTool.
2024: Yu Du, Fangyun Wei, Hongyang Zhang
https://arxiv.org/pdf/2402.04253
…
continue reading
2024: Yu Du, Fangyun Wei, Hongyang Zhang
https://arxiv.org/pdf/2402.04253
299 episoder