Imagen de Portada

Gym-Anything: Turn any Software into an Agent Environment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Aggarwal, Pranjal, Neubig, Graham, Welleck, Sean
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
por: Aggarwal, Pranjal, et al.
Publicado: (2025)

AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
por: Aggarwal, Pranjal, et al.
Publicado: (2024)

Programming with Pixels: Can Computer-Use Agents do Software Engineering?
por: Aggarwal, Pranjal, et al.
Publicado: (2025)

Agentic-R1: Distilled Dual-Strategy Reasoning
por: Du, Weihua, et al.
Publicado: (2025)

Training Proactive and Personalized LLM Agents
por: Sun, Weiwei, et al.
Publicado: (2025)

Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization
por: Agarwal, Anmol, et al.
Publicado: (2026)

miniCodeProps: a Minimal Benchmark for Proving Code Properties
por: Lohn, Evan, et al.
Publicado: (2024)

The BrowserGym Ecosystem for Web Agent Research
por: De Chezelles, Thibault Le Sellier, et al.
Publicado: (2024)

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
por: Wang, Zhun, et al.
Publicado: (2026)

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

UserBench: An Interactive Gym Environment for User-Centric Agents
por: Qian, Cheng, et al.
Publicado: (2025)

miniCTX: Neural Theorem Proving with (Long-)Contexts
por: Hu, Jiewen, et al.
Publicado: (2024)

Optimizing Temperature for Language Models with Multi-Sample Inference
por: Du, Weihua, et al.
Publicado: (2025)

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
por: Xi, Zhiheng, et al.
Publicado: (2025)

DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback
por: Khan, Zaid, et al.
Publicado: (2024)

PeersimGym: An Environment for Solving the Task Offloading Problem with Reinforcement Learning
por: Metelo, Frederico, et al.
Publicado: (2024)

PersonaGym: Evaluating Persona Agents and LLMs
por: Samuel, Vinay, et al.
Publicado: (2024)

D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery
por: Moussa, Hanane Nour, et al.
Publicado: (2026)

A Rubric-Supervised Critic from Sparse Real-World Outcomes
por: Wang, Xingyao, et al.
Publicado: (2026)

EduGym: An Environment and Notebook Suite for Reinforcement Learning Education
por: Moerland, Thomas M., et al.
Publicado: (2023)

EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings
por: Malay, Shiva Krishna Reddy, et al.
Publicado: (2026)

MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science
por: Xu, Ran, et al.
Publicado: (2025)

Recursive Agent Optimization
por: Gandhi, Apurva, et al.
Publicado: (2026)

OceanGym: A Benchmark Environment for Underwater Embodied Agents
por: Xue, Yida, et al.
Publicado: (2025)

WebArena: A Realistic Web Environment for Building Autonomous Agents
por: Zhou, Shuyan, et al.
Publicado: (2023)

Effective Strategies for Asynchronous Software Engineering Agents
por: Geng, Jiayi, et al.
Publicado: (2026)

GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning
por: Yang, Ningyuan, et al.
Publicado: (2026)

MoralityGym: A Benchmark for Evaluating Hierarchical Moral Alignment in Sequential Decision-Making Agents
por: Rosen, Simon, et al.
Publicado: (2026)

TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents
por: Cai, Yifu, et al.
Publicado: (2025)

Mining--Gym: A Configurable RL Benchmarking Environment for Truck Dispatch Scheduling
por: Banerjee, Chayan, et al.
Publicado: (2025)

ClawGym: A Scalable Framework for Building Effective Claw Agents
por: Bai, Fei, et al.
Publicado: (2026)

ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization
por: Ahuja, Riyaz, et al.
Publicado: (2026)

Mitigating Conversational Inertia in Multi-Turn Agents
por: Wan, Yang, et al.
Publicado: (2026)

CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale
por: Wang, Zhun, et al.
Publicado: (2025)

Premise Selection for a Lean Hammer
por: Zhu, Thomas, et al.
Publicado: (2025)

NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
por: Haider, Momin, et al.
Publicado: (2024)

BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery
por: Gandhi, Kanishk, et al.
Publicado: (2025)

GEM: A Gym for Agentic LLMs
por: Liu, Zichen, et al.
Publicado: (2025)

Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
por: Sun, Zhiqing, et al.
Publicado: (2024)

Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification
por: Zhao, Eric, et al.
Publicado: (2025)