# GNNs as Predictors of Agentic Workflow Performances

arXiv: https://arxiv.org/abs/2503.11301 · HTML: https://mlsanity.com/paper/2503.11301/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 33)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Simple and Deep Graph Convolutional Networks](https://mlsanity.com/paper/2007.02133/) (2020)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2003.00982/) (2020)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [A Fair Comparison of Graph Neural Networks for Graph Classification](https://mlsanity.com/paper/1912.09893/) (2019)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding](https://mlsanity.com/paper/2401.04398/) (2024)
- [LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead](https://mlsanity.com/paper/2404.04834/) (2024)
- [Self-Evolving Multi-Agent Collaboration Networks for Software Development](https://mlsanity.com/paper/2410.16946/) (2024)
- [MathChat: Converse to Tackle Challenging Math Problems with LLM Agents](https://mlsanity.com/paper/2306.01337/) (2023)
- [Building Math Agents with Multi-Turn Iterative Preference Learning](https://mlsanity.com/paper/2409.02392/) (2024)
- [CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents](https://mlsanity.com/paper/2401.10568/) (2024)
- [Benchmarking Agentic Workflow Generation](https://mlsanity.com/paper/2410.07869/) (2024)

## Built on by (most cited first, 17 of 17)

- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)
- [Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities](https://mlsanity.com/paper/2506.18019/) (2025)
- [RobustFlow: Towards Robust Agentic Workflow Generation](https://mlsanity.com/paper/2509.21834/) (2025)
- [MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2505.16988/) (2025)
- [Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects](https://mlsanity.com/paper/2507.21407/) (2025)
- [MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks](https://mlsanity.com/paper/2603.02630/) (2026)
- [On the Importance of Task Complexity in Evaluating LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2510.04311/) (2025)
- [GRADE: Graph Representation of LLM Agent Dependency and Execution](https://mlsanity.com/paper/2606.22741/) (2026)
- [Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows](https://mlsanity.com/paper/2505.19764/) (2025)
- [Learning to Compose for Cross-domain Agentic Workflow Generation](https://mlsanity.com/paper/2602.11114/) (2026)
- [FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse](https://mlsanity.com/paper/2606.11290/) (2026)
- [GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Prediction](https://mlsanity.com/paper/2512.15751/) (2025)
- [Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection](https://mlsanity.com/paper/2605.27470/) (2026)
- [Everywhere Learning: Artificial Intelligence with Pointwise Constraints](https://mlsanity.com/paper/2606.01557/) (2026)
- [Learning Samples Importance: Parameterizing Dual Variables in Everywhere Learning](https://mlsanity.com/paper/2609.36310/) (2026)
- [MoFlow: Multi-Objective Agentic Workflow Generation](https://mlsanity.com/paper/2609.38294/) (2026)

## Abstract (arXiv)

Agentic workflows invoked by Large Language Models (LLMs) have achieved remarkable success in handling complex tasks. However, optimizing such workflows is costly and inefficient in real-world applications due to extensive invocations of LLMs. To fill this gap, this position paper formulates agentic workflows as computational graphs and advocates Graph Neural Networks (GNNs) as efficient predictors of agentic workflow performances, avoiding repeated LLM invocations for evaluation. To empirically ground this position, we construct FLORA-Bench, a unified platform for benchmarking GNNs for predicting agentic workflow performances. With extensive experiments, we arrive at the following conclusion: GNNs are simple yet effective predictors. This conclusion supports new applications of GNNs and a novel direction towards automating agentic workflow optimization. All codes, models, and data are available at https://github.com/youngsoul0731/Flora-Bench.