LongHorizon-Harness：推进面向真实世界任务的长时程智能体

摘要

大语言模型（LLM）智能体越来越多地承担需要跨多个相互依赖步骤进行持续推理、工具使用和修订的长程任务。然而，现有的智能体框架在持续增长的上下文中维护任务执行、任务状态和完成度评估，这使得状态难以追踪，并使错误的自我评估得以传播到后续决策之中。我们将长程执行重新表述为任务状态管理问题，并提出LongHorizon-Harness。该框架将任务状态显式地维护在执行过程之外，且仅使用从环境中独立验证的事实来更新状态。其管理-执行-审计（MEA）循环使用管理器来维护任务状态并确定下一个子任务，使用全新上下文的执行器来执行该子任务，并使用只读审计器在下一轮开始前验证生成的环境状态。一个轻量级的智能体适配器（AgentAdapter）支持模型和框架后端的可互换使用，而无需修改其原生智能体循环。LongHorizon-Harness将Qwen~3.7-Plus在WeaveBench上的准确率从51.8%提升至80.7%，在Terminal-Bench~2.1上从69.7%提升至77.2%，在OSWorld~2.0上从2.8%提升至8.3%。它还将Claude Opus~4.7在OSWorld2.0子集上的表现从20.0%提升至34.3%，展示了跨模型、框架和交互领域的一致改进。

English

Large language model (LLM) agents increasingly undertake long-horizon tasks that require sustained reasoning, tool use, and revision across many interdependent steps. However, existing agent harnesses maintain task execution, task state, and completion assessment within a growing context, making the state difficult to track and allowing incorrect self-assessments to propagate into later decisions. We reformulate long-horizon execution as a task-state management problem and propose LongHorizon-Harness, which maintains the task state explicitly outside execution and updates it only with facts independently verified from the environment. Its Manage-Execute-Audit(MEA) loop uses a manager to maintain the task state and determine the next subtask, a fresh-context executor to perform it, and a read-only auditor to verify the resulting environment state before the next round. A lightweight AgentAdapter supports interchangeable model and harness backends without modifying their native agent loops. LongHorizon-Harness improves Qwen~3.7-Plus from 51.8% to 80.7% on WeaveBench, from 69.7% to 77.2% on Terminal-Bench~2.1, and from 2.8% to 8.3% on OSWorld~2.0. It also raises Claude Opus~4.7 from 20.0% to 34.3% on an OSWorld2.0 subset, demonstrating consistent gains across models, harnesses, and interaction domains.