Cover Image

Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Xinyu, Cai, Yuzhu, Liu, Zexi, Zheng, Bingyang, Wang, Cheng, Ye, Rui, Zhang, Yuzhi, Zhang, Linfeng, E, Weinan, Chen, Siheng, Wang, Yanfeng
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering
by: Cai, Yuzhu, et al.
Published: (2026)

EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale
by: Zhu, Xinyu, et al.
Published: (2026)

ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning
by: Liu, Zexi, et al.
Published: (2025)

SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?
by: Chai, Jingyi, et al.
Published: (2025)

ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering
by: Liu, Zexi, et al.
Published: (2025)

Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale
by: Zhang, Linfeng, et al.
Published: (2025)

Scaling Machine Learning Interatomic Potentials with Mixtures of Experts
by: Liu, Yuzhi, et al.
Published: (2026)

LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
by: Lu, Yijun, et al.
Published: (2026)

Hypergraph Transformer for Semi-Supervised Classification
by: Liu, Zexi, et al.
Published: (2023)

Incentivizing Inclusive Contributions in Model Sharing Markets
by: Zhang, Enpei, et al.
Published: (2025)

OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
by: Du, Yuwen, et al.
Published: (2026)

OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
by: Du, Yuwen, et al.
Published: (2026)

FedMABench: Benchmarking Mobile Agents on Decentralized Heterogeneous User Data
by: Wang, Wenhao, et al.
Published: (2025)

OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning
by: Ye, Rui, et al.
Published: (2024)

Towards Self-Evolving Agentic Literature Retrieval
by: Du, Yuwen, et al.
Published: (2026)

CookBench: A Long-Horizon Embodied Planning Benchmark for Complex Cooking Scenarios
by: Cai, Muzhen, et al.
Published: (2025)

AgentFold: Long-Horizon Web Agents with Proactive Context Management
by: Ye, Rui, et al.
Published: (2025)

Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation
by: Tang, Shuo, et al.
Published: (2024)

Deep Potentials for Materials Science
by: Wen, Tongqi, et al.
Published: (2022)

UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios
by: Luo, Haotian, et al.
Published: (2025)

Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
by: Lee, Yoonsang, et al.
Published: (2026)

FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models
by: Ye, Rui, et al.
Published: (2024)

The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break
by: Wang, Xinyu Jessica, et al.
Published: (2026)

Machine-Learning-Based Interatomic Potentials for Group IIB to VIA Semiconductors: Towards a Universal Model
by: Liu, Jianchuan, et al.
Published: (2023)

Leveraging Unstructured Text Data for Federated Instruction Tuning of Large Language Models
by: Ye, Rui, et al.
Published: (2024)

Towards Clustering of Incomplete Mixed‐Attribute Data
by: Chuyao Zhang, et al.
Published: (2025)

MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning
by: Ye, Juexiang, et al.
Published: (2026)

KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server
by: Wang, Wenhao, et al.
Published: (2024)

DataMaster: Data-Centric Autonomous AI Research
by: Du, Yaxin, et al.
Published: (2026)

Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
by: Zhang, Yuxiang, et al.
Published: (2025)

Toward Autonomous Long-Horizon Engineering for ML Research
by: Chen, Guoxin, et al.
Published: (2026)

Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation
by: Pang, Xianghe, et al.
Published: (2024)

Ethical-Lens: Curbing Malicious Usages of Open-Source Text-to-Image Models
by: Cai, Yuzhu, et al.
Published: (2024)

Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models
by: Ye, Rui, et al.
Published: (2024)

Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning
by: Tang, Shuo, et al.
Published: (2024)

Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models
by: Ni, Zhenyang, et al.
Published: (2024)

Toward Agentic AI: Task-Oriented Communication for Hierarchical Planning of Long-Horizon Tasks
by: Huang, Sin-Yu, et al.
Published: (2026)

PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research
by: Miao, Tingjia, et al.
Published: (2025)

MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training
by: Guo, Taicheng, et al.
Published: (2025)

ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution
by: Wang, Jihong, et al.
Published: (2026)