GenXR-Bench is a new benchmark designed to evaluate coding agents in the context of interactive extended reality (XR) development. It comprises 112 expert-authored tasks—including feature implementations, bug repairs, and application generation—alongside a testing suite that uses scripted and adaptive interactions with programmatic and visual assertions. The benchmark achieved 96.5% accuracy against expert judgments on 124 candidate applications, yet current models only reach a 50.9% Pass@1 score, highlighting challenges such as asynchronous sensor lifecycles and embodied interaction semantics.
arXiv:2609.22000v1 Announce Type: new Abstract: Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Re...
Code4Scene is a benchmark that evaluates coding agents on constructing and editing 3D scenes in Unreal Engine. It tests agents on two tasks: construction, where they must build a scene from open‑ended language, and editing, where they must recover a target scene from reference images while preserving everything else. The benchmark measures task fulfillment, artifact integrity, and physical validity, revealing that construction and editing performance are correlated but not interchangeable, with agents struggling most with spatial composition and precise edits.
arXiv:2606. 01869v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly asked not only to write static interfaces, but to construct executable interactive worlds from natural language.
The paper introduces 3DCodeVerse, a research ecosystem that allows coding agents to generate editable and verifiable 3D content at scale. It comprises a large curated dataset of 3D executable code (3DCodeVerse‑2M), a multi‑agent harness that automatically evaluates and refines generated programs using execution checks and spatial measurements, and empirical studies that establish baselines and practical guidance for 3D coding. Experiments show that fine‑tuning on the dataset improves open‑source models’ 3D coding abilities, and the harness outperforms Claude Design in pairwise human evaluations when used with Claude Opus 5.5.
arXiv:2606. 01057v1 Announce Type: cross Abstract: Procedural 3D modeling through code is emerging as a versatile paradigm, offering deterministic, engine-ready, and precisely editable assets that neural 3D generators inherently lack.
arXiv:2606. 03103v1 Announce Type: new Abstract: Real-world professional desktop workflows in specialized creative and engineering software unfold over long horizons and often require human-in-the-loop coordination, where agents proactively seek necessary information and users provide additional instructions, clarifications, feedback, or corrections as the task progresses.
DyCraft is an agentic system that generates long‑horizon 4D animated 3D scenes by decomposing the task into a detailed plan, a static scene, and a 3D storyboard of key poses. Each storyboard frame is a static scene that the agent can build and debug independently, allowing local motion to be authored with verified start and end states. In evaluations on 24 multi‑shot animation tasks, DyCraft reduces physical violations and produces higher‑quality scenes that are more often preferred by human raters compared to native GPT‑6 agents and prior baselines.
SpaceAct is a new benchmark that tests multimodal large language models on 3D spatial and temporal reasoning through closed‑loop physical action and active perception. It uses interlocking bricks and mechanical puzzles to create 108 verified instances across 36 task families, requiring models to reconstruct 3D geometry, anticipate dynamics, and execute precise 6‑DoF poses while avoiding collisions. The accompanying SAPA framework provides diagnostic modes and active‑perception capabilities, revealing that even with a valid plan, current models struggle with 3D visual grounding and action refinement.
arXiv:2610.27690v1 Announce Type: new Abstract: Simulation-ready world reconstruction demands physical interactivity beyond visual realism, which existing black-box 3D generation fails to deliver. We...
Simulation-ready world reconstruction demands physical interactivity beyond visual realism, which existing black-box 3D generation fails to deliver. We present NeoWorld-3, a coding-agent framework tha...
arXiv:2608.21833v1 Announce Type: new Abstract: Recent large language models (LLMs) can operate as coding agents that build complete games from natural language requests. Game development is especial...
arXiv:2605. 14398v3 Announce Type: replace Abstract: Video-based world models generate visually plausible rollouts, but since they infer dynamics in latent states, they enforce no explicit physical constraints: contacts drift, shapes distort, and motion loses consistency.