ai.hackcv
论文精选 65arXiv

Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents· Pack Light, CarryOn: 面向对象长期代理的背景构建

Long-horizon agents accumulate progress in persistent task state, yet repeatedly process interaction histories describing how that progress was achieved. This raises a natural question: can long-horizon context instead be organized around reusable progress rather than the history that produced it? In this paper, we introduce CarryOn, an object-oriented context runtime that organizes continuation around reusable task objects. Rather than treating compressed histories or reconstructed accounts of progress as the primary basis for continuation, CarryOn builds a context view from continuation carriers, complementary execution context, and a live tail of recent interactions. A core challenge is keeping this reusable basis valid after its surrounding history is retired: how can CarryOn update th

AI 解读论文

提出面向对象的长期代理背景构建方法,提高任务状态的可重用性和有效性。

核心方法
引入CarryOn系统,通过组合可续任务对象、补充执行上下文和最近交互的动态记录来构建任务上下文。
适合谁读
研究者、工程师
要解决的问题
长期代理在执行任务时,依赖于交互历史来累积进展,而非直接利用可重用的任务成果,导致效率低下。
关键实验
展示了CarryOn在多个长期任务场景下的性能提升,具体实验数据见论文。
主要贡献
开发了一种新的面向对象的任务上下文构建方法,能够有效管理长期代理的进展,提高其在任务中的表现。
意义与局限
CarryOn提供了一种更高效、更灵活的长期代理任务管理方式,但可能在某些特定场景下面临上下文更新的挑战。
领域:cs.AI作者:Yuchen Lu、Julian McAuley、Lei Zhang
相关推荐
论文精选 65已解读

Simulated Control Evals· 模拟控制评估

Control evaluations measure whether safeguards can prevent an AI model from causing undesi…

领域:cs.AI作者:Jeffrey Olmo、David Zhang、Tyler Tracy
📎 arXiv🕒 10-23 01:26🔗 arxiv.org

本站内容由 LLM 精选聚合,原文版权归 arXiv 所有 · 摘录仅供参考