{"ID":2856605,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.11967","arxiv_id":"2510.11967","title":"Scaling Long-Horizon LLM Agent via Context-Folding","abstract":"Large language model (LLM) agents are fundamentally constrained by context length on long-horizon tasks. We introduce Context-Folding, a framework that empowers agents to actively manage their working context. An agent can procedurally branch into a sub-trajectory to handle a subtask and then fold it upon completion, collapsing the intermediate steps while retaining a concise summary of the outcome. To make this behavior learnable, we develop an end-to-end reinforcement learning framework FoldGRPO with specific process rewards to encourage effective task decomposition and context management. On complex long-horizon tasks (Deep Research and SWE), our folding agent matches or outperforms the ReAct baselines while using an active context 10$\\times$ smaller and significantly outperforms models that rely on summarization-based context management.","short_abstract":"Large language model (LLM) agents are fundamentally constrained by context length on long-horizon tasks. We introduce Context-Folding, a framework that empowers agents to actively manage their working context. An agent can procedurally branch into a sub-trajectory to handle a subtask and then fold it upon completion, c...","url_abs":"https://arxiv.org/abs/2510.11967","url_pdf":"https://arxiv.org/pdf/2510.11967v1","authors":"[\"Weiwei Sun\",\"Miao Lu\",\"Zhan Ling\",\"Kang Liu\",\"Xuesong Yao\",\"Yiming Yang\",\"Jiecao Chen\"]","published":"2025-10-13T22:00:58Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}