Imagen de Portada

ResearchGym: Evaluating Language Model Agents on Real-World AI Research

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Garikaparthi, Aniketh, Patwardhan, Manasi, Cohan, Arman
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

IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery
por: Garikaparthi, Aniketh, et al.
Publicado: (2025)

REVERE: Reflective Evolving Research Engineer for Scientific Workflows
por: Gangireddi, Balaji Dinesh, et al.
Publicado: (2026)

Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation
por: Mule, Srujan P, et al.
Publicado: (2026)

MIR: Methodology Inspiration Retrieval for Scientific Research Problems
por: Garikaparthi, Aniketh, et al.
Publicado: (2025)

Can LLMs Perceive Time? An Empirical Investigation
por: Garikaparthi, Aniketh
Publicado: (2026)

AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research
por: Zhao, Yilun, et al.
Publicado: (2025)

Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future
por: Wu, Sihong, et al.
Publicado: (2026)

Can LLMs Identify Critical Limitations within Scientific Research? A Systematic Evaluation on AI Research Papers
por: Xu, Zhijian, et al.
Publicado: (2025)

SciMDR: Advancing Scientific Multimodal Document Reasoning
por: Chen, Ziyu, et al.
Publicado: (2026)

RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation
por: Wu, Sihong, et al.
Publicado: (2026)

ResearchCodeAgent: An LLM Multi-Agent System for Automated Codification of Research Methodologies
por: Gandhi, Shubham, et al.
Publicado: (2025)

Defend: Automated Rebuttals for Peer Review with Minimal Author Guidance
por: Khatri, Jyotsana, et al.
Publicado: (2026)

Acceleron: A Tool to Accelerate Research Ideation
por: Nigam, Harshit, et al.
Publicado: (2024)

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

WorldGym: World Model as An Environment for Policy Evaluation
por: Quevedo, Julian, et al.
Publicado: (2025)

On Evaluating LLM Alignment by Evaluating LLMs as Judges
por: Liu, Yixin, et al.
Publicado: (2025)

ANCHOR: Branch-Point Data Generation for GUI Agents
por: Wei, Jinbiao, et al.
Publicado: (2026)

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

One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs
por: Dunefsky, Jacob, et al.
Publicado: (2025)

TutorGym: A Testbed for Evaluating AI Agents as Tutors and Students
por: Weitekamp, Daniel, et al.
Publicado: (2025)

OpenComputer: Verifiable Software Worlds for Computer-Use Agents
por: Wei, Jinbiao, et al.
Publicado: (2026)

Real-World Gaps in AI Governance Research
por: Strauss, Ilan, et al.
Publicado: (2025)

Step-level Optimization for Efficient Computer-use Agents
por: Wei, Jinbiao, et al.
Publicado: (2026)

Bayesian Calibration of Win Rate Estimation with LLM Evaluators
por: Gao, Yicheng, et al.
Publicado: (2024)

ScholarGym: Benchmarking Large Language Model Capabilities in the Information-Gathering Stage of Deep Research
por: Shen, Hao, et al.
Publicado: (2026)

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

Investigating Data Contamination in Modern Benchmarks for Large Language Models
por: Deng, Chunyuan, et al.
Publicado: (2023)

Thought-For-Food: Reasoning Chain Induced Food Visual Question Answering
por: Jain, Riddhi, et al.
Publicado: (2025)

MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning
por: Tang, Xiangru, et al.
Publicado: (2023)

Deep Research Bench: Evaluating AI Web Research Agents
por: FutureSearch, et al.
Publicado: (2025)

On the Benefits of Fine-Grained Loss Truncation: A Case Study on Factuality in Summarization
por: Flores, Lorenzo Jaime Yu, et al.
Publicado: (2024)

SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation
por: Zhang, Xichen, et al.
Publicado: (2026)

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

AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
por: Xi, Zhiheng, et al.
Publicado: (2024)

Calibrating Long-form Generations from Large Language Models
por: Huang, Yukun, et al.
Publicado: (2024)

FormGym: Doing Paperwork with Agents
por: Toles, Matthew, et al.
Publicado: (2025)

PaperBench: Evaluating AI's Ability to Replicate AI Research
por: Starace, Giulio, et al.
Publicado: (2025)

Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics
por: Lee, Jinu, et al.
Publicado: (2025)

OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety
por: Vijayvargiya, Sanidhya, et al.
Publicado: (2025)

GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks
por: Patwardhan, Tejal, et al.
Publicado: (2025)