Don't Just Fine-tune the Agent, Tune the Environment
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_ | 1866917233118150656 |
|---|---|
| author | Lu, Siyuan Wang, Zechuan Zhang, Hongxuan Wu, Qintong Gan, Leilei Zhuang, Chenyi Gu, Jinjie Lin, Tao |
| author_facet | Lu, Siyuan Wang, Zechuan Zhang, Hongxuan Wu, Qintong Gan, Leilei Zhuang, Chenyi Gu, Jinjie Lin, Tao |
| contents | Large Language Model (LLM) agents show great promise for complex, multi-turn tool-use tasks, but their development is often hampered by the extreme scarcity of high-quality training data. Supervised fine-tuning (SFT) on synthetic data leads to overfitting, whereas standard reinforcement learning (RL) struggles with a critical cold-start problem and training instability. To address these challenges, we introduce $\textbf{Environment Tuning}$, a novel training paradigm that enables agents to learn complex behaviors directly from problem instances without relying on pre-collected expert trajectories. $\textbf{Environment Tuning}$ orchestrates this learning process through a structured curriculum, actionable environment augmentation that provides corrective feedback, and fine-grained progress rewards to ensure stable and efficient exploration. Using only 400 problem instances from Berkeley Function-Calling Leaderboard (BFCL) benchmark, our method not only achieves competitive in-distribution performance against strong baselines but also demonstrates superior out-of-distribution generalization, overcoming the performance collapse common to SFT-based approaches. Our work presents a paradigm shift from supervised fine-tuning on static trajectories to dynamic, environment-based exploration, paving the way for training more robust and data-efficient agents. The code is available at https://github.com/inclusionAI/AWorld-RL/tree/main/EnvTuning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10197 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Don't Just Fine-tune the Agent, Tune the Environment Lu, Siyuan Wang, Zechuan Zhang, Hongxuan Wu, Qintong Gan, Leilei Zhuang, Chenyi Gu, Jinjie Lin, Tao Artificial Intelligence Large Language Model (LLM) agents show great promise for complex, multi-turn tool-use tasks, but their development is often hampered by the extreme scarcity of high-quality training data. Supervised fine-tuning (SFT) on synthetic data leads to overfitting, whereas standard reinforcement learning (RL) struggles with a critical cold-start problem and training instability. To address these challenges, we introduce $\textbf{Environment Tuning}$, a novel training paradigm that enables agents to learn complex behaviors directly from problem instances without relying on pre-collected expert trajectories. $\textbf{Environment Tuning}$ orchestrates this learning process through a structured curriculum, actionable environment augmentation that provides corrective feedback, and fine-grained progress rewards to ensure stable and efficient exploration. Using only 400 problem instances from Berkeley Function-Calling Leaderboard (BFCL) benchmark, our method not only achieves competitive in-distribution performance against strong baselines but also demonstrates superior out-of-distribution generalization, overcoming the performance collapse common to SFT-based approaches. Our work presents a paradigm shift from supervised fine-tuning on static trajectories to dynamic, environment-based exploration, paving the way for training more robust and data-efficient agents. The code is available at https://github.com/inclusionAI/AWorld-RL/tree/main/EnvTuning. |
| title | Don't Just Fine-tune the Agent, Tune the Environment |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.10197 |