The paper introduces WorldCoder-Bench, a comprehensive benchmark and evaluation protocol for testing LLMs' ability to autonomously generate complex, physically grounded, and interactive 3D web worlds.

The paper introduces MUSE, a comprehensive benchmark that evaluates Text-to-CAD generation by assessing complex assemblies based on functionality, manufacturability, and assemblability, moving beyond…

The paper introduces EgoBench, the first interactive multimodal benchmark designed to jointly evaluate advanced AI agents' capabilities in visual perception, multi-hop reasoning, and dynamic tool usag…

The paper introduces WebIGBench, a novel benchmark designed to rigorously evaluate multimodal LLMs' ability to generate code for complex, interactive webpages, addressing the limitations of existing s…

The paper introduces Staged Executable Inverse Graphics (SEIG), an agentic framework that uses general-purpose Vision-Language Models (VLMs) to reconstruct editable 3D scenes directly into executable…

The paper introduces SABER, a new benchmark that evaluates the operational safety of LLM coding agents in complex, stateful project environments, finding that current models have a high rate of harmfu…

The paper introduces CodeGolf Bench, a novel multi-language benchmark using code golf to measure LLMs' ability to generate highly concise and efficient code, showing that reasoning models significantl…

The paper introduces AgenticVBench, a comprehensive benchmark of 100 real-world video post-production tasks, and finds that even the best AI agents perform significantly worse than human experts on th…

The paper proposes VLM3, a simple, scalable method that demonstrates standard Vision Language Models (VLMs) can natively learn 3D understanding by focusing on architectural simplicity and specific dat…

SkillsInjector proposes a two-stage adaptive method to dynamically optimize skill selection, quantity, and presentation for LLM agents, significantly improving task performance over static injection m…

The study found that while multi-agent LLM code generation architectures significantly affect code complexity, the added complexity does not translate into better functional correctness, suggesting ar…

The paper introduces CV-Arena, a large-scale open benchmark for instructional computer vision, demonstrating that professional-grade image editing requires advanced capabilities in physical reasoning…

The paper introduces TASTE, an automatic task synthesis method that generates challenging agent benchmarks by evolving tool sequences, demonstrating that existing benchmarks are saturated and that TAS…

CubePart is a generative framework that enables the creation of complex 3D meshes by explicitly controlling and generating individual, semantically defined parts based on open-vocabulary text prompts.

The paper demonstrates that specialized coding agents, using only text and image access within a sandbox, can effectively solve complex omnimodal tasks, often outperforming state-of-the-art native omn…

This paper proposes SpatialClaw, a training-free framework for spatial reasoning that enables open-ended, complex 3D/4D spatial reasoning.

BenchEvolver introduces a solution-centric evolutionary framework to automatically transform saturated coding benchmarks into significantly harder, high-quality, and diverse evaluation suites.

The paper introduces RoboTrustBench, a comprehensive benchmark that evaluates the trustworthiness of video world models for robotic manipulation across challenging scenarios, finding that current mode…

The paper experimentally evaluates 12 multi-agent LLM collaboration topologies for software design, finding that structural adversarial prompting and cross-model review are the most effective approach…