3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models

• URL: http://arxiv.org/abs/2609.06535v1
• Date: Sun, 06 Sep 2026 10:59:15 GMT
• Title: 3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models
• Abstract summary: 3DHarnessBench is a benchmark that evaluates the agentic ability of vision-correction models to recover 3D geometry as Blender Python code.<n>We observe that the ability of all frontier models to recover 3D geometry improves significantly with richer function call access.<n>We will release the benchmark, code, outputs, and agent trajectories for reproducible 3D evaluation.
• Score: 35.365323691170616
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce 3DHarnessBench, a benchmark that evaluates the agentic ability of frontier vision-language models (VLMs) to recover 3D geometry as Blender Python code from a variety of inputs. Unlike previous frameworks that prompt the VLMs with a fixed input (e.g., a single rendering or a text description), 3DHarnessBench evaluates four separate harness settings that progressively enable active agentic exploration, facilitated by recent Blender MCP functionality. Our hierarchy from Single-view, Multi-view, Active Visual (arbitrary viewpoint access), and Full 3D Interaction (complete access to the target object through Blender function calls) probes the models' abilities in both visual perception and active inference, tool calling, and self-correction. We observe that the ability of all frontier models to recover 3D geometry improves significantly with richer function call access, although the improvements are strongly model-dependent, revealing highly uneven agentic 3D-to-code capabilities. We will release the benchmark, code, outputs, and agent trajectories for reproducible 3D evaluation.

Related papers

• Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs [62.865932175477035]
  Metric 3D object detection is a core capability for embodied agents, yet most reliable systems lean on depth sensors.<n>We propose Map-Det3D, an online multi-view 3D object detection model that brings detection directly into a 3D space reconstructed from RGB.
  arXiv  Detail & Related papers  (2026-08-12T15:33:42Z)
• 3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code [25.904997126319547]
  3DCodeBench is a systematic benchmark for evaluating vision-language model (VLM) agents for procedural 3D generation in 3D modeling software.<n>We build 3DCodeArena, a ranking platform based on pairwise human preferences over generated 3D outputs.
  arXiv  Detail & Related papers  (2026-05-31T06:59:49Z)
• AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models [0.0]
  3D Visual Grounding (3DVG) is an essential capability for embodied AI, requiring agents to localize objects in 3D scenes based on natural language descriptions.<n>We present $bftextAgentGrounder$, a zero-shot 3D visual grounding framework that operates directly on colored point clouds without task-specific 3D training.
  arXiv  Detail & Related papers  (2026-05-25T14:29:04Z)
• Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding [34.1504914582344]
  3D Visual Grounding aims to localize objects in 3D scenes via natural language descriptions.<n>We propose "Think, Act, Build (TAB)", a generative 2D-to-3D reconstruction paradigm operating directly on raw RGB-D streams.<n>To overcome the multi-view coverage deficit caused by strict VLM semantic tracking, we introduce the Semantic-Anchored Geometric Expansion.
  arXiv  Detail & Related papers  (2026-04-01T06:12:16Z)
• Particulate: Feed-Forward 3D Object Articulation [89.78788418174946]
  Particulate is a feed-forward approach that, given a single static 3D mesh of an everyday object, directly infers all attributes of the underlying articulated structure.<n>We train the network end-to-end on a diverse collection of articulated 3D assets from public datasets.<n>During inference, Particulate lifts the network's feed-forward prediction to the input mesh, yielding a fully articulated 3D model in seconds.
  arXiv  Detail & Related papers  (2025-12-12T18:59:51Z)
• Evaluating Foundation Models' 3D Understanding Through Multi-View Correspondence Analysis [38.10984626023432]
  We introduce a novel benchmark for in-context 3D scene understanding that requires no finetuning and directly probes the quality of dense visual features.<n>We benchmark 8 state-of-the-art foundation models and show DINO-based encoders remain competitive across large viewpoint shifts.
  arXiv  Detail & Related papers  (2025-12-12T14:03:16Z)
• LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight [105.9472902251177]
  We present a VLM-native recipe that casts 3D detection as a next-token prediction problem.<n>Our model achieves state-of-the-art results, with 49.89 AP_3D, surpassing the previous best by +15.51 absolute improvement.
  arXiv  Detail & Related papers  (2025-11-25T18:59:45Z)
• EA3D: Online Open-World 3D Object Extraction from Streaming Videos [55.48835711373918]
  We present ExtractAnything3D (EA3D), a unified online framework for open-world 3D object extraction.<n>Given a streaming video, EA3D dynamically interprets each frame using vision-language and 2D vision foundation encoders to extract object-level knowledge.<n>A recurrent joint optimization module directs the model's attention to regions of interest, simultaneously enhancing both geometric reconstruction and semantic understanding.
  arXiv  Detail & Related papers  (2025-10-29T03:56:41Z)
• 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection [62.57179069154312]
  We introduce the first end-to-end 3D Monocular Open-set Object Detector (3D-MOOD)<n>We lift the open-set 2D detection into 3D space through our designed 3D bounding box head.<n>We condition the object queries with geometry prior and overcome the generalization for 3D estimation across diverse scenes.
  arXiv  Detail & Related papers  (2025-07-31T13:56:41Z)
• TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP [52.79100775328595]
  3D visual grounding allows an embodied agent to understand visual information in real-world 3D environments based on human instructions.<n>Existing 3D visual grounding methods rely on separate encoders for different modalities.<n>We propose a unified 2D pre-trained multi-modal network to process all three modalities.
  arXiv  Detail & Related papers  (2025-07-20T10:28:06Z)
• Regulating Intermediate 3D Features for Vision-Centric Autonomous Driving [26.03800936700545]
  We propose to regulate intermediate dense 3D features with the help of volume rendering. Experimental results on the Occ3D and nuScenes datasets demonstrate that Vampire facilitates fine-grained and appropriate extraction of dense 3D features.
  arXiv  Detail & Related papers  (2023-12-19T04:09:05Z)
• PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm [111.16358607889609]
  We introduce a novel universal 3D pre-training framework designed to facilitate the acquisition of efficient 3D representation.<n>For the first time, PonderV2 achieves state-of-the-art performance on 11 indoor and outdoor benchmarks, implying its effectiveness.
  arXiv  Detail & Related papers  (2023-10-12T17:59:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.