Jiaxin Ge, Junyi Zhang, Tianning Chai, Hanjun Yoo, Chenyang Wang, Xiuyu Li, Weijia Shi, XuDong Wang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26845 · open-access PDF
一个看似合理的冲击在Sokoban可以使谜团无法解决。为了避免这样的错误,代理人必须在执行之前预见其行为的后果,特别是当来自真实环境的反馈稀缺或行为不可逆转时。我们引入了代理想象(Agima),一个培训框架,训练代理人在行动之前想象,即想象。
Machine translation (Meta M2M100); the English original follows.
A seemingly reasonable push in Sokoban can make the puzzle unsolvable. To avoid such mistakes, an agent has to anticipate the consequences of its actions before execution, especially when feedback from the real environment is sparse or actions are irreversible. We introduce Agentic Imagination (Agima), a training framework that trains an agent to imagine before acting, i.e. to be imaginative. Agima trains a single omni model to propose actions, generate images of their outcomes, and then reason over these imagined futures to decide what to execute in the real environment. Rather than committin
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26845, 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