探索信息寻求智能体整合
Exploring Information Seeking Agent Consolidation
AI总结:
通过系统实证研究,比较数据级混合与参数级合并两种范式,发现参数级合并能以更低成本达到数据混合的性能,并保留跨域能力。
摘要:
信息寻求智能体已成为知识密集型任务的有力范式,但当今系统仍局限于开放网络、文档或本地知识库,阻碍了可扩展的跨域部署。我们首次系统性地实证研究了将这些信息寻求智能体整合为单一基础智能体模型。我们比较了两种范式——\emph{数据级混合}(在混合数据集上训练统一模型)和\emph{参数级合并}(在参数空间中合并独立训练的专家)——涵盖3种训练场景,在\textbf{10}个基准上评估了\textbf{26}种代表性参数级方法。为了比较异构基准,我们引入了几何复合分数和不平衡分数,分别描述整体性能和任务偏斜。我们的分析表明:(i) 设计良好的参数级合并以极低的训练成本达到数据混合的性能,且与顺序无关;(ii) 参数级合并结构性地保留了数据混合普遍遗忘的域外能力;(iii) 跨场景稳定性与整合质量密切相关。我们将观察结果提炼为方法选择指南和下一代合并算子的设计原则。
英文摘要:
Information-seeking agents have emerged as a powerful paradigm for knowledge-intensive tasks, yet today's systems remain specialized for the open web, documents, or local knowledge bases, hindering scalable and cross-domain deployment. We present the first systematic empirical study of consolidating these information-seeking agents into a single foundation agentic model. We compare two paradigms -- \emph{data-level mixing}, which trains a unified model on a mixture of datasets, and \emph{parameter-level merging}, which merges independently trained experts in parameter space -- across 3 training scenarios, evaluating \textbf{26} representative parameter-level methods on \textbf{10} benchmarks. To compare across heterogeneous benchmarks, we introduce a geometric Composite Score and an Imbalance Score that describe overall performance and task skew. Our analysis shows that (i) well-designed parameter-level merging attains parity with data mixing at a fraction of its training cost and is order-agnostic; (ii) parameter-level merging structurally preserves out-of-domain capabilities that data mixing universally forgets; and (iii) cross-scenario stability is strongly tied to consolidation quality. We distil our observations into a method-selection guide and design principles for next-generation merging operators.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。