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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Du, Shiyi, Liu, Jiayuan, Du, Weihua, Huang, Yue, Li, Jiayi, Luo, Yingtao, Zhang, Xiangliang, Conitzer, Vincent, Kingsford, Carl
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

Shutdown Safety Valves for Advanced AI
di: Conitzer, Vincent
Pubblicazione: (2026)

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

Amortized Bayesian Workflow
di: Li, Chengkun, et al.
Pubblicazione: (2024)

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

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

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

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

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

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

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

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

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

AFlow: Automating Agentic Workflow Generation
di: Zhang, Jiayi, et al.
Pubblicazione: (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
di: Wei Luo, et al.
Pubblicazione: (2024)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Local Inverse Geometry Can Be Amortized
di: Kachhadiya, Aaditya L.
Pubblicazione: (2026)

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

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