Cover Image

From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yue, Ling, Bhandari, Kushal Raj, Ko, Ching-Yun, Patel, Dhaval, Lin, Shuxin, Zhou, Nianjun, Gao, Jianxi, Chen, Pin-Yu, Pan, Shaowu
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Chat-of-Thought: Collaborative Multi-Agent System for Generating Domain Specific Information
by: Constantinides, Christodoulos, et al.
Published: (2025)

Unraveling the cognitive patterns of Large Language Models through module communities
by: Bhandari, Kushal Raj, et al.
Published: (2025)

Forecasting Open-Weight AI Model Growth on HuggingFace
by: Bhandari, Kushal Raj, et al.
Published: (2025)

Towards Automated Solution Recipe Generation for Industrial Asset Management with LLM
by: Zhou, Nianjun, et al.
Published: (2024)

Optimizing Waste Management with Advanced Object Detection for Garbage Classification
by: Kuang, Everest Z., et al.
Published: (2024)

Results and Retrospective Analysis of the CODS 2025 AssetOpsBench Challenge
by: Patel, Dhaval, et al.
Published: (2026)

Toward a Trustworthy Optimization Modeling Agent via Verifiable Synthetic Data Generation
by: Lima, Vinicius, et al.
Published: (2025)

Exploring the Robustness of Language Models for Tabular Question Answering via Attention Analysis
by: Bhandari, Kushal Raj, et al.
Published: (2024)

Towards Building General Purpose Embedding Models for Industry 4.0 Agents
by: Constantinides, Christodoulos, et al.
Published: (2025)

vLLM Hook v0: A Plug-in for Programming Model Internals on vLLM
by: Ko, Ching-Yun, et al.
Published: (2026)

CRAFT: Training-Free Cascaded Retrieval for Tabular QA
by: Singh, Adarsh, et al.
Published: (2025)

Improving Robustness of Tabular Retrieval via Representational Stability
by: Bhandari, Kushal Raj, et al.
Published: (2026)

Foam-Agent: Towards Automated Intelligent CFD Workflows
by: Yue, Ling, et al.
Published: (2025)

Fine-Tuned Thoughts: Leveraging Chain-of-Thought Reasoning for Industrial Asset Health Monitoring
by: Lin, Shuxin, et al.
Published: (2025)

AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance
by: Patel, Dhaval, et al.
Published: (2025)

Agentproof: Static Verification of Agent Workflow Graphs
by: Xavier, Melwin, et al.
Published: (2026)

LLM Assisted Anomaly Detection Service for Site Reliability Engineers: Enhancing Cloud Infrastructure Resilience
by: Jha, Nimesh, et al.
Published: (2025)

SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks
by: Ozaki, Yusuke, et al.
Published: (2026)

Causal Past Logic for Runtime Verification of Distributed LLM Agent Workflows
by: Bollig, Benedikt
Published: (2026)

Foam-Agent 2.0: An End-to-End Composable Multi-Agent Framework for Automating CFD Simulation in OpenFOAM
by: Yue, Ling, et al.
Published: (2025)

MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
by: Ganapavarapu, Giridhar, et al.
Published: (2026)

DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules
by: De Silva, Devin Yasith, et al.
Published: (2026)

PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools
by: Feng, Tianjun, et al.
Published: (2026)

Code-Guided Reasoning for Small Language Models: Evaluating Executable MCQA Scaffolds
by: Biswas, Prateek, et al.
Published: (2026)

Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines
by: Merchant, Alimurtaza Mustafa, et al.
Published: (2026)

Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
by: Lee, Yu-Ang, et al.
Published: (2026)

Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding
by: Guan, Yue, et al.
Published: (2025)

KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows
by: Pan, Zaifeng, et al.
Published: (2025)

Agent WARPP: Workflow Adherence via Runtime Parallel Personalization
by: Mazzolenis, Maria Emilia, et al.
Published: (2025)

Adaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoring
by: Gil, Natalia Martinez, et al.
Published: (2026)

SAGE: Hierarchical LLM-Based Literary Evaluation through Ontology-Grounded Interpretive Dimensions
by: Wang, Tianyu, et al.
Published: (2026)

ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization
by: Wang, Yinjie, et al.
Published: (2025)

Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Models
by: Arif, Huzaifa, et al.
Published: (2025)

FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes
by: Constantinides, Christodoulos, et al.
Published: (2025)

AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents
by: Somasekharan, Nithin, et al.
Published: (2026)

Graph-Memoized Reasoning: Foundations Structured Workflow Reuse in Intelligent Systems
by: Singh, Yash Raj
Published: (2025)

Cerberus: Multi-Agent Reasoning and Coverage-Guided Exploration for Static Detection of Runtime Errors
by: Dhulipala, Hridya, et al.
Published: (2025)

Beyond the Kolmogorov Barrier: A Learnable Weighted Hybrid Autoencoder for Model Order Reduction
by: Somasekharan, Nithin, et al.
Published: (2024)

On the lifting and reconstruction of nonlinear systems with multiple invariant sets
by: Pan, Shaowu, et al.
Published: (2023)

Graph is all you need? Lightweight data-agnostic neural architecture search without training
by: Huang, Zhenhan, et al.
Published: (2024)