GOAT: A Training Framework for Goal-Oriented Agent with Tools

Large language models (LLMs) have evolved from pure text generators into interactive agents capable of invoking external tools.However, LLM agents still struggle with goal-oriented queries, which require decomposing high-level objectives into sequences of interdependent API calls with accurate planning and execution.Current approaches rely on zero-shot evaluation due to the absence of training data; while proprietary models such as GPT-4 exhibit strong reasoning capabilities, smaller opensource models remain ineffective at complex tool use.To address this limitation, we propose a novel training framework GOAT, that enables fine-tuning LLM agents without human annotation.GOAT automatically synthesizes goal-oriented API execution data from API documents using a novel call-first generation paradigm, that constructs training data based on executed API call sequences.Through extensive experiments, we show that GOATtrained agents achieve state-of-the-art performance across multiple existing goal-oriented benchmarks.In addition, we introduce GOAT-Bench, a new goal-oriented API execution benchmark, and demonstrate that agents trained with GOAT also excel in this setting.These results highlight GOAT as a practical path toward building robust open-source LLM agents capable of complex reasoning and tool use.