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
En este informe, presentamos Sage-A1.5, un modelo de agencia de 35B Mix-of-Experts que se basa en A1 para avanzar en la resolución de problemas de agentes de largo horizonte a través de la composición de capacidad de colaboración adaptativa. En comparación con A1, Sage-A1.5 aprende no solo a resolver tareas individuales, sino también a organizar el trabajo y revisar su enfoque durante la ejecución. Sage-A1.5 destaca tres mejoras prácticas: orquestación de agentes, verificación y descubrimiento científico abierto. En primer lugar, la orquestación de agentes de discusión extiende la ejecución de agentes únicos a través de la delegación de tareas y la colaboración paralela entre subagentes con contextos aislados, permitiendo al agente descomponer tareas complejas
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