GOAT: A Training Framework for Goal-Oriented Agent with Tools
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909010896093184 |
|---|---|
| author | Min, Hyunji Jung, Sangwon Sung, Junyoung Lee, Dosung Han, Leekyeung Seo, Paul Hongsuck |
| author_facet | Min, Hyunji Jung, Sangwon Sung, Junyoung Lee, Dosung Han, Leekyeung Seo, Paul Hongsuck |
| contents | 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 open-source 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 GOAT-trained agents achieve state-of-the-art performance across multiple existing goal-oriented benchmarks. In addition, we introduce GOATBench, 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12218 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GOAT: A Training Framework for Goal-Oriented Agent with Tools Min, Hyunji Jung, Sangwon Sung, Junyoung Lee, Dosung Han, Leekyeung Seo, Paul Hongsuck Artificial Intelligence 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 open-source 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 GOAT-trained agents achieve state-of-the-art performance across multiple existing goal-oriented benchmarks. In addition, we introduce GOATBench, 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. |
| title | GOAT: A Training Framework for Goal-Oriented Agent with Tools |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.12218 |