Sejoon Chang | Searcharxiv

arXiv2026

GameEngineBench: Evaluating Coding Agents on Real C++ Runtime Environments

Game engines provide real-time simulation, rendering, physics, interaction, networking, and asset pipelines, making them valuable not only for games but also for 3D applications in healthcare, robotics, architecture, manufacturing, and related domains. Because game development is where these systems are most mature and publicly available, it offers a practical testbed for evaluating coding agents that must modify C++ code within stateful, interactive, real-time systems. We present GameEngineBench, a benchmark for evaluating coding agents on scoped C++ implementation tasks inside Unreal Engine 5 projects, built from nine real-world game repositories. The evaluation set consists of 110 tasks spanning gameplay mechanics, multiplayer behavior, AI and world orchestration, animation and movement, UI and session code, loading behavior, online-service integration, persistence, data serialization, XR behavior, and rendering-oriented plugins. These tasks require models to make native C++ changes that compile and satisfy behavioral tests within executable Unreal Engine projects. Across twelve evaluated configurations, the strongest model reaches 55.5\% pass@1, while 31 tasks remain unsolved by every configuration. Our results demonstrate that frontier coding agents continue to struggle with deeply integrated C++ development for real-time interactive software, highlighting game-engine benchmarks as a valuable complement to existing software engineering evaluations.

cs.SE↗

arXiv2025

Enhancing Critical Thinking with AI: A Tailored Warning System for RAG Models

Retrieval-Augmented Generation (RAG) systems offer a powerful approach to enhancing large language model (LLM) outputs by incorporating fact-checked, contextually relevant information. However, fairness and reliability concerns persist, as hallucinations can emerge at both the retrieval and generation stages, affecting users' reasoning and decision-making. Our research explores how tailored warning messages -- whose content depends on the specific context of hallucination -- shape user reasoning and actions in an educational quiz setting. Preliminary findings suggest that while warnings improve accuracy and awareness of high-level hallucinations, they may also introduce cognitive friction, leading to confusion and diminished trust in the system. By examining these interactions, this work contributes to the broader goal of AI-augmented reasoning: developing systems that actively support human reflection, critical thinking, and informed decision-making rather than passive information consumption.

cs.HC↗