Imagen de Portada

ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhou, Jingqi, Wang, Sheng, Deng, Dezhao, Lu, Junwen, Su, Junwei, Li, Qintong, Gao, Jiahui, Wu, Hao, Jiang, Jiyue, Kong, Lingpeng, Jin, Dunhong, Wu, Chuan
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning
por: Wang, Sheng, et al.
Publicado: (2025)

LoRA Meets Dropout under a Unified Framework
por: Wang, Sheng, et al.
Publicado: (2024)

ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom
por: Zhou, Jingqi, et al.
Publicado: (2024)

MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards
por: Wang, Sheng, et al.
Publicado: (2024)

Data Augmentation of Multi-turn Psychological Dialogue via Knowledge-driven Progressive Thought Prompting
por: Jiang, Jiyue, et al.
Publicado: (2024)

Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks
por: Li, Qintong, et al.
Publicado: (2023)

Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration
por: Li, Qintong, et al.
Publicado: (2024)

PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA
por: Wang, Sheng, et al.
Publicado: (2024)

DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
por: Zhao, Xueliang, et al.
Publicado: (2025)

How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models
por: Jiang, Jiyue, et al.
Publicado: (2024)

Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models
por: Jiang, Jiyue, et al.
Publicado: (2025)

GeomHerd: A Forward-looking Herding Quantification via Ricci Flow Geometry on Agent Interactive Simulations
por: Yang, Lake, et al.
Publicado: (2026)

Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent
por: Xia, Bowei, et al.
Publicado: (2026)

GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers
por: Li, Qintong, et al.
Publicado: (2024)

QSpec: Speculative Decoding with Complementary Quantization Schemes
por: Zhao, Juntao, et al.
Publicado: (2024)

Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution
por: Xu, Yechen, et al.
Publicado: (2024)

When Do Multi-Agent Systems Outperform? Analysing the Learning Efficiency of Agentic Systems
por: Su, Junwei, et al.
Publicado: (2026)

On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks
por: Su, Junwei, et al.
Publicado: (2025)

A Non-Asymptotic Convergent Analysis for Scored-Based Graph Generative Model via a System of Stochastic Differential Equations
por: Su, Junwei, et al.
Publicado: (2025)

On the Topology Awareness and Generalization Performance of Graph Neural Networks
por: Su, Junwei, et al.
Publicado: (2024)

ToolGate: Contract-Grounded and Verified Tool Execution for LLMs
por: Liu, Yanming, et al.
Publicado: (2026)

MSPipe: Efficient Temporal GNN Training via Staleness-Aware Pipeline
por: Sheng, Guangming, et al.
Publicado: (2024)

Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark
por: Wu, Mengsong, et al.
Publicado: (2024)

Self-Infilling Code Generation
por: Zheng, Lin, et al.
Publicado: (2023)

Leave No One Behind: Online Self-Supervised Self-Distillation for Sequential Recommendation
por: Wei, Shaowei, et al.
Publicado: (2024)

Designing and Validating a Self-Aligning Tool Changer for Modular Reconfigurable Manipulation Robots
por: Maskur, Mahfudz, et al.
Publicado: (2026)

The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
por: Li, Junlong, et al.
Publicado: (2025)

ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution
por: Huang, Xu, et al.
Publicado: (2025)

A Principle-Driven Adaptive Policy for Group Cognitive Stimulation Dialogue for Elderly with Cognitive Impairment
por: Jiang, Jiyue, et al.
Publicado: (2026)

Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution
por: He, Kaiwen, et al.
Publicado: (2025)

Improving Implicit Regularization of SGD with Preconditioning for Least Square Problems
por: Su, Junwei, et al.
Publicado: (2024)

On the Limitation and Experience Replay for GNNs in Continual Learning
por: Su, Junwei, et al.
Publicado: (2023)

PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks
por: Su, Junwei, et al.
Publicado: (2024)

UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
por: Liang, Yijuan, et al.
Publicado: (2026)

Emergent Wigner-Dyson Statistics and Self-Attention-Based Prediction in Driven Bose-Hubbard Chains
por: Wu, Chen-Huan
Publicado: (2022)

Scaling Reasoning without Attention
por: Zhao, Xueliang, et al.
Publicado: (2025)

Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning
por: Wang, Li, et al.
Publicado: (2026)

Tool-Planner: Task Planning with Clusters across Multiple Tools
por: Liu, Yanming, et al.
Publicado: (2024)

Reflection-Based Task Adaptation for Self-Improving VLA
por: Li, Baicheng, et al.
Publicado: (2025)

OS-Copilot: Towards Generalist Computer Agents with Self-Improvement
por: Wu, Zhiyong, et al.
Publicado: (2024)