OpenGameEval: Benchmarking Agentic Programming and Exploration in a Stateful Game Engine
cs.LG, cs.AI
Submitted: 2026-10-01
Updated: 2026-10-01
Comments: A shorter version appears at the NeurIPS 2026 Workshop on Evaluation of Interactive Agents
Code: https://github.com/Roblox/open-game-eval
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Program Synthesis with Large Language Models
- Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs
- Measuring what Matters: Construct Validity in Large Language Model Benchmarks
- Evaluating Large Language Models Trained on Code
- GameDevBench: Evaluating Agentic Capabilities Through Game Development
- SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- Beyond pass@1: A Reliability Science Framework for Long-Horizon LLM Agents
- metabench -- A Sparse Benchmark of Reasoning and Knowledge in Large Language Models
- Let's Verify Step by Step
- AgentBench: Evaluating LLMs as Agents
- GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
- AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
- tinyBenchmarks: evaluating LLMs with fewer examples
- Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors
- Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- GAIA: a benchmark for General AI Assistants
- Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations
- Exploration and Exploitation Errors Are Measurable for Language Model Agents
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks