Cover Image

Rethinking Agent Design: From Top-Down Workflows to Bottom-Up Skill Evolution

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Du, Jiawei, Wu, Jinlong, Chen, Yuzheng, Hu, Yucheng, Li, Bing, Zhou, Joey Tianyi
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bottom-Up and Top-Down Analysis of Values, Agendas, and Observations in Corpora and LLMs
by: Friedman, Scott E., et al.
Published: (2024)

Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents
by: Ma, Tianyi, et al.
Published: (2025)

Infinite Ends from Finite Samples: Open-Ended Goal Inference as Top-Down Bayesian Filtering of Bottom-Up Proposals
by: Zhi-Xuan, Tan, et al.
Published: (2024)

EH-Benchmark Ophthalmic Hallucination Benchmark and Agent-Driven Top-Down Traceable Reasoning Workflow
by: Pan, Xiaoyu, et al.
Published: (2025)

From Text to Simulation: A Multi-Agent LLM Workflow for Automated Chemical Process Design
by: Tian, Xufei, et al.
Published: (2026)

SAG-Agent: Enabling Long-Horizon Reasoning in Strategy Games via Dynamic Knowledge Graphs
by: Tang, Chenwei, et al.
Published: (2025)

Causality from Bottom to Top: A Survey
by: Weinberg, Abraham Itzhak, et al.
Published: (2024)

Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents
by: Ma, Tianmi, et al.
Published: (2025)

Trace2Skill: Verifier-Guided Skill Evolution for Long-Context EDA Agents
by: Du, Zijian, et al.
Published: (2026)

Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition
by: Jia, Xuemei, et al.
Published: (2026)

AppAgentX: Evolving GUI Agents as Proficient Smartphone Users
by: Jiang, Wenjia, et al.
Published: (2025)

Rethinking the AI Scientist: Interactive Multi-Agent Workflows for Scientific Discovery
by: Weidener, Lukas, et al.
Published: (2026)

SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
by: Zhang, Ziao, et al.
Published: (2026)

FlowAgent: Achieving Compliance and Flexibility for Workflow Agents
by: Shi, Yuchen, et al.
Published: (2025)

Tracking Skiers from the Top to the Bottom
by: Dunnhofer, Matteo, et al.
Published: (2023)

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
by: Shi, Yaorui, et al.
Published: (2026)

Learning to Be A Doctor: Searching for Effective Medical Agent Architectures
by: Zhuang, Yangyang, et al.
Published: (2025)

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
by: Yang, Yutao, et al.
Published: (2026)

Position: AI Scaling: From Up to Down and Out
by: Wang, Yunke, et al.
Published: (2025)

The Art of Tool Interface Design
by: Wu, Yunnan, et al.
Published: (2025)

Memento-Skills: Let Agents Design Agents
by: Zhou, Huichi, et al.
Published: (2026)

Skill-R1: Agent Skill Evolution via Reinforcement Learning
by: Vishe, Yash, et al.
Published: (2026)

Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
by: Wu, Xiyang, et al.
Published: (2026)

CUA-Skill: Develop Skills for Computer Using Agent
by: Chen, Tianyi, et al.
Published: (2026)

Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
by: Liu, Dawei, et al.
Published: (2026)

SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents
by: Zhou, Yifan, et al.
Published: (2026)

RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation
by: Wu, Hang, et al.
Published: (2025)

From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents
by: Zhang, Xiaolei, et al.
Published: (2026)

Cognitive Inception: Agentic Reasoning against Visual Deceptions by Injecting Skepticism
by: Zhao, Yinjie, et al.
Published: (2025)

From LLM-anation to LLM-orchestrator: Coordinating Small Models for Data Labeling
by: Lu, Yao, et al.
Published: (2025)

SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
by: Xu, Duling, et al.
Published: (2026)

Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision
by: Kalluri, Tarun, et al.
Published: (2023)

Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution
by: Xiong, Feng, et al.
Published: (2026)

LAMMI-Pathology: A Tool-Centric Bottom-Up LVLM-Agent Framework for Molecularly Informed Medical Intelligence in Pathology
by: Su, Haoyang, et al.
Published: (2026)

Automated Multi-Agent Workflows for RTL Design
by: Bhattaram, Amulya, et al.
Published: (2025)

Counterfactual Trace Auditing of LLM Agent Skills
by: Zhou, Xiaolin, et al.
Published: (2026)

From Intent to Execution: Composing Agentic Workflows with Agent Recommendation
by: Athrey, Kishan, et al.
Published: (2026)

AEGIS: Authenticity Evaluation Benchmark for AI-Generated Video Sequences
by: Li, Jieyu, et al.
Published: (2025)

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
by: Liu, Hongyi, et al.
Published: (2026)

ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning
by: Li, Yu, et al.
Published: (2026)