Cover Image

Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dennis, Simon, Patil, Rivaan, Shabahang, Kevin, Guo, Hao
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When Mean CE Fails: Median CE Can Better Track Language Model Quality
by: Guo, Hao, et al.
Published: (2026)

In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks
by: Dennis, Simon, et al.
Published: (2026)

Beyond Inference-Only Deployment: Comparing Weight-Based Consolidation Against Cascading Compaction
by: Dennis, Simon, et al.
Published: (2026)

Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows
by: Trirat, Patara, et al.
Published: (2025)

Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
by: Pan, Haolin, et al.
Published: (2025)

Agentics 2.0: Logical Transduction Algebra for Agentic Data Workflows
by: Gliozzo, Alfio Massimiliano, et al.
Published: (2026)

Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning
by: Choi, Moonseok, et al.
Published: (2023)

Optimizing Agentic Workflows using Meta-tools
by: Abuzakuk, Sami, et al.
Published: (2026)

MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
by: Zhang, Aozhong, et al.
Published: (2024)

GeoFlow: Agentic Workflow Automation for Geospatial Tasks
by: Bhattaram, Amulya, et al.
Published: (2025)

Flow: Modularized Agentic Workflow Automation
by: Niu, Boye, et al.
Published: (2025)

Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization
by: Yao, Yihang, et al.
Published: (2026)

Estimating Worst-Case Frontier Risks of Open-Weight LLMs
by: Wallace, Eric, et al.
Published: (2025)

RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows
by: Mahdavi, Hamed, et al.
Published: (2025)

CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting
by: Pan, Bokai, et al.
Published: (2026)

Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
by: Liu, Yong, et al.
Published: (2024)

Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection
by: Huang, Tairan, et al.
Published: (2026)

Generalized Orders of Magnitude for Scalable, Parallel, High-Dynamic-Range Computation
by: Heinsen, Franz A., et al.
Published: (2025)

Agentic NL2SQL to Reduce Computational Costs
by: Jehle, Dominik, et al.
Published: (2025)

AnaFlow: Agentic LLM-based Workflow for Reasoning-Driven Explainable and Sample-Efficient Analog Circuit Sizing
by: Ahmadzadeh, Mohsen, et al.
Published: (2025)

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
by: Zeng, Yifan, et al.
Published: (2026)

OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic Workflows
by: Dai, Ruiting, et al.
Published: (2026)

AFlow: Automating Agentic Workflow Generation
by: Zhang, Jiayi, et al.
Published: (2024)

Finding the Sweet Spot: Trading Quality, Cost, and Speed During Inference-Time LLM Reflection
by: Butler, Jack, et al.
Published: (2025)

Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents
by: Liu, Zhihan, et al.
Published: (2026)

Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
by: Ding, Dujian, et al.
Published: (2024)

To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration
by: Yang, Zeyu, et al.
Published: (2025)

The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation
by: Cheng, Shuaizhi, et al.
Published: (2026)

The Primacy of Magnitude in Low-Rank Adaptation
by: Zhang, Zicheng, et al.
Published: (2025)

GLOW: Graph-Language Co-Reasoning for Agentic Workflow Performance Prediction
by: Guan, Wei, et al.
Published: (2025)

Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity
by: Ran, Yide, et al.
Published: (2025)

The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM
by: Lee, Kwanhee, et al.
Published: (2025)

Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents
by: Li, Yushu, et al.
Published: (2026)

Learning to Compose for Cross-domain Agentic Workflow Generation
by: Wang, Jialiang, et al.
Published: (2026)

Evaluating Multimodal LLMs for Inpatient Diagnosis: Real-World Performance, Safety, and Cost Across Ten Frontier Models
by: Bassett, Bruce A., et al.
Published: (2026)

Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL
by: Zheng, Kunhao, et al.
Published: (2026)

Benchmarking Agentic Workflow Generation
by: Qiao, Shuofei, et al.
Published: (2024)

Foundations and Frontiers of Graph Learning Theory
by: Huang, Yu, et al.
Published: (2024)

An LLM-Tool Compiler for Fused Parallel Function Calling
by: Singh, Simranjit, et al.
Published: (2024)

Syntax- and Compilation-Preserving Evasion of LLM Vulnerability Detectors
by: Sun, Luze, et al.
Published: (2026)