Wenjie Lou, Tianshuo Peng, Shiyang Feng, Shengji Tang, Runmin Ma, Ruizhe Chen, Jinxin Shi, Haoyang Peng, Fangchen Yu, Zhijie Zhong, Yuhao Zhou, Yue Fan, Yixin Chen, Yiming Wu, Yiheng Wang, Yigeng Jiang, Yichen Jiang, Yi Xie, Xu Guo, Xiaohan He · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.28578 · cited by 0 works (OpenAlex) · open-access PDF
在本报告中,我们介绍了Sage-A1.5,一个基于A1的35B混合专家代理模型,通过适应性协作能力组合来推进长期代理问题的解决。与A1相比,Sage-A1.5不仅学会解决个别任务,还能够在执行过程中组织工作并修订其方法。Sage-A1.5突出了三个改进:代理管制,验证和开放科学发现。第一,代理管制通过分配任务和与孤立背景的子代理之间并行协作扩展单代理的互动执行,使复杂任务能够在执行过程中分解并同时解决。Sage-A1.5突出了三个改进:代理管制,验证和开放科学发现。第二,代理管制通过进行进展检查,验证,验证和反思策略,使代理人能够识别非生产性的病例,并通过多
Machine translation (Meta M2M100); the English original follows.
In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1, Sage-A1.5 learns not only to solve individual tasks, but also to organize work and revise its approach during execution. Sage-A1.5 highlights three improvements: agentic orchestration, verification, and open scientific discovery. First, agentic orchestration extends single-agent execution through task delegation and parallel collaboration among subagents with isolated contexts, enabling complex tasks to be decomposed and addressed concurrently and supporting efficient execution while reducing interference across concurrent subagents. Second, agentic verification strengthens long-horizon reliability through progress checking, evidence validation, and reflective strategy revision, allowing the agent to recognize unproductive search paths and pursue alternative approaches. Third, open scientific discovery extends agentic capabilities beyond answering predefined questions to conducting exploratory research, connecting scientific inquiry with interactive analysis and inspectable research artifacts. We showcase these capabilities through complicated agentic tasks and multidisciplinary scientific applications. Besides, we hope Sage-A1.5 provides the community with an accessible foundation for open scientific discovery, offering a practical path from long-horizon task execution to collaborative, verifiable, and inspectable scientific exploration.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Orchestration, Computer science, Task (project management), Data science, Multidisciplinary approach, Reliability (semiconductor)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28578, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange