Episode
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
- Podcast
- Daily Paper Cast
- Published
- Jul 1, 2026
- Duration seconds
- 1583
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/1744418d
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/scaling-the-horizon-not-the-parameters-reaching-trillion-parameter-performance-with-a-35b-agent/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/scaling-the-horizon-not-the-parameters-reaching-trillion-parameter-performance-with-a-35b-agent.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 69 | cs.CL Authors: Lei Bai, Zongsheng Cao, Yang Chen, Zhiyao Cui, Shangheng Du, Yue Fan, Shiyang Feng, Zijie Guo, Haonan He, Liang He, Xiaohan He, Shuyue Hu, Yusong Hu, Songtao Huang, Yichen Jiang, Hao Li, Xin Li, Dahua Lin, Weihao Lin, Fenghua Ling, Dongrui Liu, Zhuo Liu, Runmin Ma, Chunjiang Mu, Haoyang Peng, Tianshuo Peng, Jinxin Shi, Luohe Shi, Boyuan Sun, Zelin Tan, Shengji Tang, Qianyi Wang, Yiming Wu, Yi Xie, Xiangchao Yan, Jingqi Ye, Peng Ye, Fangchen Yu, Jiakang Yuan, Bihao Zhan, Bo Zhang, Chen Zhang, Shufei Zhang, Shuaiyu Zhang, Wenlong Zhang, Yiqun Zhang, Junpeng Zhao, Zhijie Zhong, Bowen Zhou, Yuhao Zhou Title: Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent Arxiv: http://arxiv.org/abs/2606.30616v1 Abstract: We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling from two perspectives: scaling long-horizon trajectories and scaling heterogeneous agent abilities. To support this goal, we build a long-horizon knowledge-action infrastructure that connects external knowledge, actions, observations, and verifier outcomes, producing agentic trajectories with an average length of 45K tokens. Based on this, we train Agents-A1 with a three-stage recipe. First, we perform full-domain supervised fine-tuning to align the base model with broad agentic behaviors. Second, we train domain-level teacher models to capture specialized expertise in each domain. Third, we propose a multi-teacher domain-routed on-policy distillation with salient vocabulary alignment to improve knowledge transfer efficiency across different domains, unifying six heterogeneous domains into one deployable student mod…