Copertina

ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tu, Dunwei, Hao, Hongyan, Yang, Hansi, Chen, Yihao, Zhang, Yi-Kai, Xia, Zhikang, Yang, Yu, Sun, Yueqing, Liu, Xingchen, Shen, Furao, Gu, Qi, Su, Hui, Cai, Xunliang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
di: Xu, Minrui, et al.
Pubblicazione: (2026)

TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training
di: Yang, Jinluan, et al.
Pubblicazione: (2026)

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
di: Song, Xiaoshuai, et al.
Pubblicazione: (2026)

daVinci-Env: Open SWE Environment Synthesis at Scale
di: Fu, Dayuan, et al.
Pubblicazione: (2026)

$V_{0.5}$: Generalist Value Model as a Prior for Sparse RL Rollouts
di: Zhang, Yi-Kai, et al.
Pubblicazione: (2026)

$V_0$: A Generalist Value Model for Any Policy at State Zero
di: Zhang, Yi-Kai, et al.
Pubblicazione: (2026)

Large-Scale Diverse Synthesis for Mid-Training
di: Zhang, Xuemiao, et al.
Pubblicazione: (2025)

Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning
di: Yi, Huiyu, et al.
Pubblicazione: (2026)

Multiple Queries with Multiple Keys: A Precise Prompt Matching Paradigm for Prompt-based Continual Learning
di: Tu, Dunwei, et al.
Pubblicazione: (2025)

Embedding Space Allocation with Angle-Norm Joint Classifiers for Few-Shot Class-Incremental Learning
di: Tu, Dunwei, et al.
Pubblicazione: (2024)

VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications
di: He, Wei, et al.
Pubblicazione: (2025)

ShuttleEnv: An Interactive Data-Driven RL Environment for Badminton Strategy Modeling
di: Li, Ang, et al.
Pubblicazione: (2026)

Prioritization Method for Crowdsourced Test Report by Integrating Text and Image Information
di: Huijie Tu, et al.
Pubblicazione: (2025)

World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
di: Xiao, Junjin, et al.
Pubblicazione: (2025)

Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch
di: Zeng, Yirong, et al.
Pubblicazione: (2025)

EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents
di: Zala, Abhay, et al.
Pubblicazione: (2024)

Scaling Sparse and Dense Retrieval in Decoder-Only LLMs
di: Zeng, Hansi, et al.
Pubblicazione: (2025)

AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning
di: Zhang, Jiayi, et al.
Pubblicazione: (2025)

ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for Agents
di: Lu, Yuxing, et al.
Pubblicazione: (2026)

Inference-Time Scaling for Generalist Reward Modeling
di: Liu, Zijun, et al.
Pubblicazione: (2025)

ResearchEnvBench: Benchmarking Agents on Environment Synthesis for Research Code Execution
di: Wang, Yubang, et al.
Pubblicazione: (2026)

Unraveling the Mystery of Scaling Laws: Part I
di: Su, Hui, et al.
Pubblicazione: (2024)

Community Detection of Directed Network for Software Ecosystems Based on a Two‐Step Information Dissemination Model
di: Huijie Tu, et al.
Pubblicazione: (2025)

EnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment Simulation
di: Liu, Yi, et al.
Pubblicazione: (2026)

Scaling and Transferability of Annealing Strategies in Large Language Model Training
di: Wang, Siqi, et al.
Pubblicazione: (2025)

Scaling Agents for Computer Use
di: Gonzalez-Pumariega, Gonzalo, et al.
Pubblicazione: (2025)

EnvBridge: Bridging Diverse Environments with Cross-Environment Knowledge Transfer for Embodied AI
di: Kagaya, Tomoyuki, et al.
Pubblicazione: (2024)

DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
di: Chen, Aili, et al.
Pubblicazione: (2026)

ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset
di: Yang, Chen, et al.
Pubblicazione: (2025)

EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modeling
di: Xia, Songpengcheng, et al.
Pubblicazione: (2024)

EnvBench: A Benchmark for Automated Environment Setup
di: Eliseeva, Aleksandra, et al.
Pubblicazione: (2025)

Scaling Generalist Data-Analytic Agents
di: Qiao, Shuofei, et al.
Pubblicazione: (2025)

Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
di: Agashe, Saaket, et al.
Pubblicazione: (2025)

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch
di: Liu, Zheng, et al.
Pubblicazione: (2026)

ToolRM: Towards Agentic Tool-Use Reward Modeling
di: Li, Renhao, et al.
Pubblicazione: (2025)

Communication-Efficient and Privacy-Preserving Decentralized Meta-Learning
di: Yang, Hansi, et al.
Pubblicazione: (2024)

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
di: Wang, Bowen, et al.
Pubblicazione: (2026)

AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints
di: Zeng, Yirong, et al.
Pubblicazione: (2026)

GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
di: Guo, Jiacheng, et al.
Pubblicazione: (2025)

SortingEnv: An Extendable RL-Environment for an Industrial Sorting Process
di: Maus, Tom, et al.
Pubblicazione: (2025)