Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.12928 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912431939256320 |
|---|---|
| author | Zhu, King Li, Hanhao Wu, Siwei Xing, Tianshun Ma, Dehua Tang, Xiangru Liu, Minghao Yang, Jian Liu, Jiaheng Jiang, Yuchen Eleanor Zhang, Changwang Lin, Chenghua Wang, Jun Zhang, Ge Zhou, Wangchunshu |
| author_facet | Zhu, King Li, Hanhao Wu, Siwei Xing, Tianshun Ma, Dehua Tang, Xiangru Liu, Minghao Yang, Jian Liu, Jiaheng Jiang, Yuchen Eleanor Zhang, Changwang Lin, Chenghua Wang, Jun Zhang, Ge Zhou, Wangchunshu |
| contents | Scaling test time compute has shown remarkable success in improving the reasoning abilities of large language models (LLMs). In this work, we conduct the first systematic exploration of applying test-time scaling methods to language agents and investigate the extent to which it improves their effectiveness. Specifically, we explore different test-time scaling strategies, including: (1) parallel sampling algorithms; (2) sequential revision strategies; (3) verifiers and merging methods; (4)strategies for diversifying rollouts.We carefully analyze and ablate the impact of different design strategies on applying test-time scaling on language agents, and have follow findings: 1. Scaling test time compute could improve the performance of agents. 2. Knowing when to reflect is important for agents. 3. Among different verification and result merging approaches, the list-wise method performs best. 4. Increasing diversified rollouts exerts a positive effect on the agent's task performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12928 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Scaling Test-time Compute for LLM Agents Zhu, King Li, Hanhao Wu, Siwei Xing, Tianshun Ma, Dehua Tang, Xiangru Liu, Minghao Yang, Jian Liu, Jiaheng Jiang, Yuchen Eleanor Zhang, Changwang Lin, Chenghua Wang, Jun Zhang, Ge Zhou, Wangchunshu Artificial Intelligence Scaling test time compute has shown remarkable success in improving the reasoning abilities of large language models (LLMs). In this work, we conduct the first systematic exploration of applying test-time scaling methods to language agents and investigate the extent to which it improves their effectiveness. Specifically, we explore different test-time scaling strategies, including: (1) parallel sampling algorithms; (2) sequential revision strategies; (3) verifiers and merging methods; (4)strategies for diversifying rollouts.We carefully analyze and ablate the impact of different design strategies on applying test-time scaling on language agents, and have follow findings: 1. Scaling test time compute could improve the performance of agents. 2. Knowing when to reflect is important for agents. 3. Among different verification and result merging approaches, the list-wise method performs best. 4. Increasing diversified rollouts exerts a positive effect on the agent's task performance. |
| title | Scaling Test-time Compute for LLM Agents |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2506.12928 |