arXiv AI

Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning

arXiv:2606. 07602v1 Announce Type: cross Abstract: LLM-based LEGO assembly generation requires both semantic grounding and physical feasibility.

arXiv AI

Jun 6

Brick-Composer: Using MLLMs for Assembly with Diverse Bricks

arXiv:2606. 05445v1 Announce Type: new Abstract: We dream of AI agents that can read arbitrary designs and construct real-world objects from reusable building blocks.

By Jiateng Liu, Bingxuan Li, Zhenhailong Wang, Rushi Wang, Kaiwen Hong, Cheng Qian, Jiayu Liu, Denghui Zhang, Katherine Driggs-Campbell, Manling Li, Heng Ji

llms agents computer-vision multimodal benchmarks

arXiv AI

Aug 11

LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?

arXiv:2503. 19990v4 Announce Type: replace Abstract: Many real-world applications of spatial intelligence, such as robotic control, autonomous driving, and automated assembly, require spatial reasoning across multiple sequential steps.

By Kexian Tang, Junyao Gao, Yanhong Zeng, Haodong Duan, Yanan Sun, Zhening Xing, Wenran Liu, Kai Chen, Kaifeng Lyu

llms agents diffusion robotics multimodal benchmarks

arXiv AI

Jul 14

PhysMRV: Physical Memory Retrieval and Verification for Physics Plausibility Reasoning

arXiv:2607. 10190v1 Announce Type: cross Abstract: Video-language models (VLMs) have achieved remarkable performance on video understanding and visual question answering, yet they remain unreliable in reasoning about physical plausibility, where understanding object interactions, causal dynamics, and fundamental physical principles is essential.

By Wenyuan Wang, Lianyu Hu, Hao Wang, Yang Liu

llms rag nlp fine-tuning multimodal benchmarks

arXiv Computer Vision

Aug 25

OmniCAD: A Large-Scale Benchmark for 3D Spatial Reasoning in Robotics Assemblies

arXiv:2608.22637v1 Announce Type: new Abstract: Recent vision-language models (VLMs) show strong capabilities in robotic perception and spatial reasoning, yet their ability to reason about complex me...

By Mingjia Wang, Taiting Lu, Ziwei Dong, Sisong Bei, Jingying Zeng, Runze Liu, Kaiyuan Lin, Hongxing Pan, Kai Zhang, Yizheng Hou, Yangshoudu Zheng, Chenchen Guo, Weiyuan Meng, Shubin Lyu, Zhijun Zheng, Dexu Wang, Xinyu Bai, Shurui Qian, Zhangzixin, Mengyu Pan, Guoliang Shi, Ling Ma, Yifan Yang, Qi He, Yi-Chao Chen, Yincheng Jin, Sung-Liang Chen, Mahanth Gowda

llms agents robotics multimodal benchmarks

Hugging Face Trending Papers

Aug 23

OmniCAD: A Large-Scale Benchmark for 3D Spatial Reasoning in Robotics Assemblies

Recent vision-language models (VLMs) show strong capabilities in robotic perception and spatial reasoning, yet their ability to reason about complex mechanical assemblies remains underexplored. We int...

llms agents robotics multimodal benchmarks

arXiv Computation and Language

Aug 25

Decoupled Physical Modeling and Execution for Physics Reasoning

The paper introduces a framework that separates physical modeling from execution in physics reasoning tasks. It uses a two‑stage post‑training approach: supervised fine‑tuning to build structured models and reinforcement learning with rubric‑based feedback to refine them. Experiments on PhysReason, PhyX, and SeePhys show that this explicit modeling improves reasoning performance by about 3% on average for small LLMs.

By Ye Zhang, Xuehang Guo, Rui Pan, Pengfei Yu, Denghui Zhang, Manling Li, Qingyun Wang

llms reinforcement-learning robotics fine-tuning multimodal benchmarks

arXiv AI

Jul 1

Embodied CAD: Solver-Grounded LLM Agents for Parametric B-Rep Assembly Modeling

arXiv:2606. 31252v1 Announce Type: new Abstract: Large language models can write plausible CAD scripts, but reliable industrial CAD modeling requires more than syntactically valid code: every feature, placement, and assembly relation must be accepted by an exact geometric kernel while remaining editable as parametric boundary representation geometry.

By Fumin Liu, Haoyu Zhou, Fei Hao, Lin Yang

llms agents robotics benchmarks

arXiv AI

Aug 18

BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization

arXiv:2605. 26182v2 Announce Type: replace Abstract: Generating physically buildable brick structures from 3D shapes requires more than geometric reconstruction: the output must also satisfy discrete part constraints and structural stability.

By Zhengyang Ni, Feng Yan, Yu Guo, Fei Wang

nlp safety

arXiv Computer Vision

Sep 4

Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning

The paper introduces FactoSR, a factorized reinforcement learning framework designed to improve spatial reasoning in Vision‑Language Models by addressing a dimensional mismatch between 2D visual inputs and the 3D+temporal nature of the physical world. FactoSR decomposes the reasoning task into three orthogonal geometric sub‑objectives—planar correspondence (XY), depth consistency (Z), and temporal reversibility (T)—and optimizes these constraints within a unified policy learning mechanism. Experiments on multi‑view and video benchmarks show that this decomposition yields significant performance gains, achieving a 5.9% improvement on VSI‑Bench and 4.5% on All‑Angles‑Bench.

By Yijun Yang, Shenghe Zheng, Wenbo Li, Jianhui Liu, Haoze Sun, Yanbing Zhang, Jiaxiu Jiang, Lin Song, Haoyang Huang, Nan Duan, Lei Zhu

llms reinforcement-learning multimodal benchmarks

arXiv Computation and Language

Sep 15

PhysMent: An Interactive Approach For LLM Reasoning In Physics Problems

arXiv:2609.13152v1 Announce Type: new Abstract: Large language models (LLMs) perform strongly on static science benchmarks, yet their ability to reason about the physical world through active experim...

By Joseph Chan, Utkarsh Jha, Xiyin Yang, Abhinav Jarajapu, Anik Sahai, Eddie Hu, Robin Jeshua Deepak, Stefano Saravalle, Aditya Shah

llms agents robotics benchmarks

Hugging Face Trending Papers

Sep 3

Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning

The paper introduces FactoSR, a factorized reinforcement learning framework designed to improve spatial reasoning in Vision‑Language Models (VLMs). By decomposing the problem into planar correspondence (XY), depth consistency (Z), and temporal reversibility (T), FactoSR addresses the dimensional mismatch between 2D visual inputs and 3D physical reasoning. Experiments on multi‑view and video benchmarks show significant performance gains, with a 5.9% improvement on VSI‑Bench and 4.5% on All‑Angles‑Bench.

llms reinforcement-learning multimodal benchmarks

arXiv AI

Jun 10

RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning

arXiv:2510. 14828v3 Announce Type: replace Abstract: Improving the reasoning capabilities of embodied agents is crucial for robots to complete complex human instructions in long-view manipulation tasks successfully.

By Jinrui Liu, Bingyan Nie, Boyu Li, Yaran Chen, Yuze Wang, Shunsen He, Haoran Li

llms agents reinforcement-learning robotics fine-tuning benchmarks

Related stories