Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Du, Shiyi, Liu, Jiayuan, Du, Weihua, Huang, Yue, Li, Jiayi, Luo, Yingtao, Zhang, Xiangliang, Conitzer, Vincent, Kingsford, Carl
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration
by: Liu, Jiayuan, et al.
Published: (2026)

CodonMoE: DNA Language Models for mRNA Analyses
by: Du, Shiyi, et al.
Published: (2025)

The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents
by: Liu, Jiayuan, et al.
Published: (2026)

Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation
by: Li, Jiayi, et al.
Published: (2026)

An Interpretable Automated Mechanism Design Framework with Large Language Models
by: Liu, Jiayuan, et al.
Published: (2025)

Why should we ever automate moral decision making?
by: Conitzer, Vincent
Published: (2024)

Amortized Variational Inference: When and Why?
by: Margossian, Charles C., et al.
Published: (2023)

Designing Rules for Choosing a Winner in a Debate
by: Heckett, Alexander, et al.
Published: (2025)

Shutdown Safety Valves for Advanced AI
by: Conitzer, Vincent
Published: (2026)

The Complexity of Computing Robust Mediated Equilibria in Ordinal Games
by: Conitzer, Vincent
Published: (2024)

Amortized Bayesian Workflow
by: Li, Chengkun, et al.
Published: (2024)

Choosing What Game to Play without Selecting Equilibria: Inferring Safe (Pareto) Improvements in Binary Constraint Structures
by: Oesterheld, Caspar, et al.
Published: (2025)

Why Generate When You Can Transform? Unleashing Generative Attention for Dynamic Recommendation
by: Liu, Yuli, et al.
Published: (2025)

Can CDT rationalise the ex ante optimal policy via modified anthropics?
by: Cooper, Emery, et al.
Published: (2024)

DyFlow: Dynamic Workflow Framework for Agentic Reasoning
by: Wang, Yanbo, et al.
Published: (2025)

Computationally Efficient High-Dimensional Bayesian Optimization via Variable Selection
by: Shen, Yihang, et al.
Published: (2021)

Why Pool When You Can Flow? Active Learning with GFlowNets
by: Zhang, Renfei, et al.
Published: (2025)

How Many Votes is a Lie Worth? Measuring Strategyproofness through Resource Augmentation
by: Berker, Ratip Emin, et al.
Published: (2026)

Game Transformations That Preserve Nash Equilibria or Best-Response Sets
by: Tewolde, Emanuel, et al.
Published: (2021)

Agentic-R1: Distilled Dual-Strategy Reasoning
by: Du, Weihua, et al.
Published: (2025)

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

Comparative Study of the Mechanical, Electronic Structure, and Optical Properties of Cubic Lithium‐Based Perovskite LiMgX3 (X = Cl, Br, I) under Pressure Effects: First‐Principles Calculations
by: Wei Luo, et al.
Published: (2024)

Turnpike with Uncertain Measurements: Triangle-Equality ILP with a Deterministic Recovery Guarantee
by: Elder, C. S., et al.
Published: (2026)

Procedural Knowledge Improves Agentic LLM Workflows
by: Hsiao, Vincent, et al.
Published: (2025)

RobustFlow: Towards Robust Agentic Workflow Generation
by: Xu, Shengxiang, et al.
Published: (2025)

Fused-Planes: Why Train a Thousand Tri-Planes When You Can Share?
by: Kassab, Karim, et al.
Published: (2024)

Computing Optimal Equilibria in Repeated Games with Restarts
by: Berker, Ratip Emin, et al.
Published: (2024)

TSAgent: An Agentic Workflow for Autonomous Transition State Search
by: Madhavan, Varun, et al.
Published: (2026)

Agentic Mixture-of-Workflows for Multi-Modal Chemical Search
by: Callahan, Tiffany J., et al.
Published: (2025)

Amortized Causal Discovery with Prior-Fitted Networks
by: Sypniewski, Mateusz, et al.
Published: (2025)

Amortized Posterior Sampling with Diffusion Prior Distillation
by: Mammadov, Abbas, et al.
Published: (2024)

Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts
by: Montreuil, Yannis, et al.
Published: (2025)

Why Evolve When You Can Adapt? Post-Evolution Adaptation of Genetic Memory for On-the-Fly Control
by: Hammami, Hamze, et al.
Published: (2025)

Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation
by: Sun, Shiyi, et al.
Published: (2026)

Optimization Problem Solving Can Transition to Evolutionary Agentic Workflows
by: Li, Wenhao, et al.
Published: (2025)

Imagining Design Workflows in Agentic AI Futures
by: Wadinambiarachchi, Samangi, et al.
Published: (2025)

Agentic Workflows for Economic Research: Design and Implementation
by: Dawid, Herbert, et al.
Published: (2025)

Local Inverse Geometry Can Be Amortized
by: Kachhadiya, Aaditya L.
Published: (2026)

GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation
by: Yang, Cehao, et al.
Published: (2025)

New Difference Triangle Sets by an FPGA-Based Search Technique
by: Shehadeh, Mohannad, et al.
Published: (2025)