Newest papers

Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition

Wenjie Lou, Tianshuo Peng, Shiyang Feng, Shengji Tang, Runmin Ma, Ruizhe Chen, Jinxin Shi, Haoyang Peng · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28578 · open-access PDF

Portuguese

Neste relatório, apresentamos o Sage-A1.5, um modelo de agente 35B que se baseia no A1 para avançar na resolução de problemas de longo horizonte através da composição de capacidade adaptativa. Em comparação com o A1, o Sage-A1.5 aprende não apenas a resolver tarefas individuais, mas também a organizar o trabalho e rever sua abordagem durante a execução. O Sage-A1.5 destaca três melhorias: orquestração agente, verificação e descoberta científica aberta. Primeiro, a orquestração agente estende a execução de agente único através da delegação de tarefas e colaboração paralela entre subagentes com contextos isolados, permitindo tarefas complexas.

Machine translation (Meta M2M100); the English original follows.

Abstract

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

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: 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.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange