arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.15751cs.LGcs.AIcs.MA
收藏

GLOW:基于图-语言协同推理的代理工作流性能预测

GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Prediction

School of Computer Science, Shanghai Jiao Tong University, China(上海交通大学计算机科学学院);Institute of Data Science, National University of Singapore, Singapore(新加坡国立大学数据科学研究所);School of Computer Engineering and Science, Shanghai University, China(上海大学计算机工程与科学学院)

Wei Guan, Jian Cao, Jinyu Cai, Qiqi Cai, Jianqi Gao, See-Kiong Ng

AI总结:

GLOW通过结合图神经网络与大语言模型,提出了一种统一的代理工作流性能预测框架,有效捕捉拓扑依赖和语义逻辑,提升预测准确性与排序效用。

摘要:

代理工作流(AWs)已逐渐成为解决复杂任务的一种有前景的范式。然而,自动化生成其可扩展性严重受限于基于执行评估的高成本和延迟。现有的AW性能预测方法仅作为替代方案,但未能同时捕捉AW中复杂的拓扑依赖关系和深层语义逻辑。为了解决这一限制,我们提出了GLOW,一个统一的AW性能预测框架,结合了GNNs的图结构建模能力和LLMs的推理能力。具体来说,我们引入了一个面向图的LLM,其在图任务上进行指令微调,以提取拓扑感知的语义特征,这些特征与GNN编码的结构表示融合。对比对齐策略进一步细化潜在空间,以区分高质量的AWs。在FLORA-Bench上的广泛实验表明,GLOW在预测准确性和排序效用方面均优于最先进的基线方法。

英文摘要:

Agentic Workflows (AWs) have emerged as a promising paradigm for solving complex tasks. However, automatically generating high-quality AWs remains expensive because AW optimization requires evaluating a large number of candidate AWs via execution, resulting in high computational cost and latency. Recently, AW performance prediction has become a hot research topic to avoid costly execution-based evaluation, but existing methods primarily use Graph Neural Networks (GNNs) to model workflow structures and insufficiently capture the semantic relationships among agents. To address this limitation, we propose GLOW, a unified framework for AW performance prediction that combines the graph-structure modeling ability of GNNs with the topology-aware semantic encoding capability of LLMs. Specifically, a graph-oriented LLM is first built through instruction-tuning on graph understanding tasks to extract topology-aware semantic representations from descriptive text of AWs. Meanwhile, a GNN explicitly models the structural information of AWs and produces corresponding structural representations. The semantic and structural representations are then fused in a shared latent space using a Transformer-based fusion module. A contrastive learning strategy is further introduced to learn more discriminative representations for AWs. Experiments on the FLORA-Bench benchmark demonstrate that GLOW consistently outperforms state-of-the-art baselines in both prediction accuracy and ranking utility. Moreover, when integrated into the AFLOW, an automatic AW generation framework, GLOW reduces optimization time by 98.7% with only a 0.031 average score decrease across three datasets, showing its effectiveness as an efficient surrogate evaluator for AW optimization.

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。

↑