Spatial Atlas: Compute-Grounded Reasoning for Spatial-Aware Research Agent Benchmarks

2026-04-13 · Arun Sharma arxiv

We introduce compute-grounded reasoning (CGR), a design paradigm for spatial-aware research agents in which every answerable sub-problem is resolved by deterministic computation before a language model is asked to generate. Spatial Atlas instantiates CGR as a single Agent-to-Agent (A2A) server that handles two challenging benchmarks: FieldWorkArena, a multimodal spatial question-answering benchmark spanning factory, warehouse, and retail environments, and MLE-Bench, a suite of 75 Kaggle machine learning competitions requiring end-to-end ML engineering. A structured spatial scene graph engine extracts entities and relations from vision descriptions, computes distances and safety violations deterministically, then feeds computed facts to large language models, thereby avoiding hallucinated spatial reasoning. Entropy-guided action selection maximizes information gain per step and routes queries across a three-tier frontier model stack (OpenAI + Anthropic). A self-healing ML pipeline with strategy-aware code generation, a score-driven iterative refinement loop, and a prompt-based leak audit registry round out the system. We evaluate across both benchmarks and show that CGR yields competitive accuracy while maintaining interpretability through structured intermediate representations and deterministic spatial computations.

📄 PDF Abstract BibTeX arXiv:2604.12102

Code (0)

등록된 구현이 없습니다.

Tasks

Spatial Reasoning Code Generation

AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents

2026-05-18 · Pan Wang, Yihao Hu, Xiujin Liu, Jingchu Yang 외 arxiv

Vision-language model (VLM) agents increasingly rely on memory-augmented reinforcement learning to reuse experience across long-horizon tasks, yet most existing frameworks store memory as text and depend on proprietary t…

Reinforcement Learning Decision Making

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

2025-11-10 · Hunar Batra, Haoqin Tu, Hardy Chen, Yuanze Lin 외 arxiv

Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning. Existing spatial MLLMs rely on large-scale datasets, explicit 3D input…

Scene Graph Generation Reinforcement Learning Spatial Reasoning Visual Reasoning

AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models

2026-08-07 · Guiyu Zhao, Longteng Guo, Yanghong Mei, Zilin Zhu 외 hf

While Vision-Language-Action (VLA) models have advanced embodied AI, their fundamentally reactive paradigm severely limits performance in partially observable and long-horizon tasks. When restricted to a single wrist-mou…

Spatial Reasoning

TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation

2026-03-19 · Yan Shu, Bin Ren, Zhitong Xiong, Xiao Xiang Zhu 외 arxiv

Vision-language models (VLMs) have shown promise in earth observation (EO), yet they struggle with tasks that require grounding complex spatial reasoning in precise pixel-level visual representations. To address this pro…

Temporal Sequences Spatial Reasoning Visual Reasoning

RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents

2026-05-11 · Imad Aouali, Flavian Vasile, Otmane Sakhi, Alexandre Gilotte 외 arxiv

LLM recommendation agents increasingly produce structured recommendation reports: sets of items accompanied by natural-language justifications. Yet existing evaluations often reduce this setting to reranking small shortl…