Imagen de Portada

Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fang, Tianqing, Zhang, Zhisong, Wang, Xiaoyang, Wang, Rui, Qin, Can, Wan, Yuxuan, Ma, Jun-Yu, Zhang, Ce, Chen, Jiaqi, Li, Xiyun, Wang, Yonglin, Ni, Jingchen, Zheng, Tianshi, Chen, Chun, Yu, Wenhao, Liang, Zhenwen, Zhang, Hongming, Mi, Haitao, Yu, Dong
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms
por: Zhang, Zhisong, et al.
Publicado: (2025)

WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model
por: Fang, Tianqing, et al.
Publicado: (2025)

VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models
por: Zhang, Ce, et al.
Publicado: (2025)

WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models
por: Wang, Rui, et al.
Publicado: (2025)

Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots
por: Zhang, Hongming, et al.
Publicado: (2024)

Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation
por: Ma, Junyu, et al.
Publicado: (2025)

MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment
por: Shi, Yucheng, et al.
Publicado: (2025)

WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback
por: Hu, Minda, et al.
Publicado: (2025)

Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding
por: Wang, Wenkai, et al.
Publicado: (2026)

Guided Self-Evolving LLMs with Minimal Human Supervision
por: Yu, Wenhao, et al.
Publicado: (2025)

Verified Critical Step Optimization for LLM Agents
por: Li, Mukai, et al.
Publicado: (2026)

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
por: Deng, Chenlong, et al.
Publicado: (2025)

InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing
por: Li, Shuaiyi, et al.
Publicado: (2025)

Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning
por: Panaganti, Kishan, et al.
Publicado: (2026)

R-Zero: Self-Evolving Reasoning LLM from Zero Data
por: Huang, Chengsong, et al.
Publicado: (2025)

LASER: LLM Agent with State-Space Exploration for Web Navigation
por: Ma, Kaixin, et al.
Publicado: (2023)

OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas
por: Wang, Xiaoyang, et al.
Publicado: (2025)

OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization
por: He, Hongliang, et al.
Publicado: (2024)

Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
por: Shi, Yucheng, et al.
Publicado: (2026)

DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
por: Jing, Liqiang, et al.
Publicado: (2024)

Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models
por: Zhang, Zhisong, et al.
Publicado: (2024)

Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification
por: Wan, Yuxuan, et al.
Publicado: (2026)

The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas
por: Xu, Baixuan, et al.
Publicado: (2025)

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration
por: Zhang, Qifan, et al.
Publicado: (2026)

Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning
por: Liang, Zhenwen, et al.
Publicado: (2025)

World-Model-Augmented Web Agents with Action Correction
por: Shen, Zhouzhou, et al.
Publicado: (2026)

Retrieval-augmented GUI Agents with Generative Guidelines
por: Xu, Ran, et al.
Publicado: (2025)

SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning
por: Zheng, Tianshi, et al.
Publicado: (2026)

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
por: Liang, Zhenwen, et al.
Publicado: (2026)

Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
por: Ouyang, Xu, et al.
Publicado: (2024)

Locas: Your Models are Principled Initializers of Locally-Supported Parametric Memories
por: Lu, Sidi, et al.
Publicado: (2026)

Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
por: Zhou, Yujun, et al.
Publicado: (2025)

On Kernel Design for Regularized Volterra Series Identification of Wiener-Hammerstein Systems
por: Xu, Yu, et al.
Publicado: (2025)

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

RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments
por: Zhang, Linghua, et al.
Publicado: (2026)

WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
por: He, Hongliang, et al.
Publicado: (2024)

Scaling Synthetic Data Creation with 1,000,000,000 Personas
por: Ge, Tao, et al.
Publicado: (2024)

MIRIX: Multi-Agent Memory System for LLM-Based Agents
por: Wang, Yu, et al.
Publicado: (2025)

Fault‐Tolerant Time‐Varying Formation Tracking for Multi‐Agent Systems With Varying Number of Agents and Mixed Cyber Attacks
por: Kunzhong Miao, et al.
Publicado: (2025)

MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions
por: Liang, Zhenwen, et al.
Publicado: (2024)