一个能长期管理复杂任务的智能体框架，让大模型更稳定地完成跨领域日常任务。
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
- 将长周期任务拆解为可控子任务，动态维护执行记忆
- 在104项任务上达成0.821的最新性能，跨5个模型通用
- 无需调参即可适配不同大模型，适合构建可靠智能体系统
大型语言模型智能体正被用于涵盖工作、学习和生活的开放式日常请求。这些任务具有长时程、跨环境和多模态特点，要求智能体在多步操作中保持目标与约束，并应对异构工具和附件。尽管已有研究分别解决目标漂移、状态丢失和上下文溢出等问题，但能否通过单一框架协同管理这些挑战并跨后端保持有效仍缺乏深入探索。本文提出 OneDayAgent，一种面向长周期任务的智能体管理框架。该框架将开放式请求转化为受控执行流程，通过任务分解、上下文压力下的执行记忆维护，以及最终成果的验证与修复实现稳健运行。我们在 AgentIF-OneDay 数据集的104项任务上进行评估，使用 GLM-5.2 后端时取得0.821的总体得分，创下新纪录。同一套框架在来自三个模型家族的五个不同大模型上运行，展现出无需调优的跨后端泛化能力，即使不同模型在相同工作流下表现出各异的执行风格。
原文摘要 · Abstract (English)
LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life. These tasks are long-horizon, cross-environment, and multimodal, forcing the agent to preserve goals and constraints across many steps while navigating heterogeneous tools and attachments. While prior work has addressed individual failure modes such as goals drift, states loss, and context overflow, whether a single harness can manage them jointly and remain effective across backends has received less study. We present OneDayAgent, a long-horizon harness for autonomous agents. OneDayAgent turns an open-ended request into a managed execution process that decomposes tasks into bounded subtasks, maintains execution memory under context pressure, and verifies and repairs the final deliverable. We evaluate OneDayAgent on AgentIF-OneDay across 104 tasks. With the GLM-5.2 backend, OneDayAgent sets a new state of the art with an overall score of 0.821. The same harness runs across five backend LLMs from three model families, indicating the harness generalizes across backends without tuning, even as different models induce distinct execution styles under the same workflow.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。