Studying Without a Syllabus: Task-Agnostic Environment Preprocessing

论文概要

研究领域: NLP
作者: Vinay Samuel, Varun Ursekar, Vijay S. Kalmath
发布时间: 2026-09-11
arXiv: 2509.05820

中文摘要

在LLM智能体处理新环境中的任务前，它可以检查可用语料库和工具并构建可复用资源，如索引、脚本或程序指导。然而大多数自动适应方法依赖任务示例、轨迹或评估反馈来决定构建什么。现有任务无关方法避免这种监督，但提前承诺针对特定环境类型的准备策略。我们研究更开放的设定：智能体能否在没有教学大纲的情况下学习不熟悉的环境，即在测试前且不了解下游任务分布的情况下，并选择如何准备？我们形式化任务无关环境预处理，其中学习系统在预算内探索环境并为冻结求解器生成产物。我们在六个异构基准上比较无辅助和档案装备的元智能体与固定合成练习和语料处理方法。元智能体变体在五个基准上取得最高Avg@3奖励，而固定语料处理在最大语料基准上仍最佳。更大的学习预算不能可靠提升下游奖励。尽管如此，学习产物减少达到给定分数所需的测试时采样，展示可复用准备如何将计算从重复测试尝试转移到任务前学习阶段。

原文摘要

Before an LLM agent tackles tasks in a new environment, it can inspect available corpora and tools and construct reusable resources such as indices, scripts, or procedural guidance. Most automated adaptation methods, however, rely on task examples, trajectories, or evaluation feedback to决定 what to build. Existing task-agnostic approaches avoid this supervision but commit in advance to a preparation strategy for a particular type of environment. We study a more open-ended setting: can an agent study an unfamiliar environment without a syllabus, i.e. before test time and without knowledge of the downstream task distribution, and choose how to prepare it? We formalize task-agnostic environment preprocessing, in which a studying system explores an environment under a budget and produces artifa...

自动采集于 2026-09-12

#论文 #arXiv #NLP #小凯