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

• URL: http://arxiv.org/abs/2604.12102v2
• Date: Wed, 15 Apr 2026 03:29:47 GMT
• Title: Spatial Atlas: Compute-Grounded Reasoning for Spatial-Aware Research Agent Benchmarks
• Abstract summary: We introduce compute-grounded reasoning (CGR) for spatial-aware research agents.<n>CGR is a design paradigm for spatial-aware research agents in which every answerable sub-problem is resolved by deterministic computation.<n>We show that CGR yields competitive accuracy while maintaining interpretability.
• Score: 1.5229257192293202
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning [99.49739831030388]
  We study how the design of this interface shapes the agent's capacity for open-ended spatial reasoning.<n>We propose SpatialClaw, a training-free framework for spatial reasoning that adopts code as the action interface.
  arXiv  Detail & Related papers  (2026-06-11T17:59:36Z)
• From Reactive to Map-Based AI: Tuned Local LLMs for Semantic Zone Inference in Object-Goal Navigation [0.7734726150561086]
  Object-Goal Navigation (ObjectNav) requires an agent to find and navigate to a target object category in unknown environments.<n>We propose a transition from reactive AI to "Map-Based AI" by integrating LLM-based semantic inference with a hybrid topological-grid mapping system.<n>Our framework employs a fine-tuned Llama-2 model via Low-Rank Adaptation (LoRA) to infer semantic zone categories and target existence probabilities from verbalized object observations.
  arXiv  Detail & Related papers  (2026-03-09T08:27:28Z)
• LaSSM: Efficient Semantic-Spatial Query Decoding via Local Aggregation and State Space Models for 3D Instance Segmentation [21.566771922153027]
  We introduce LaSSM, which prioritizes simplicity and efficiency while maintaining competitive performance.<n>We also present a coordinate-guided state space model (SSM) decoder that progressively refines queries.<n>LaSSM ranks first place on the latest ScanNet++ V2 leaderboard, outperforming the previous best method by 2.5% mAP with only 1/3 FLOPs.
  arXiv  Detail & Related papers  (2026-02-11T16:34:12Z)
• A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces [34.59674580962045]
  We introduce A-RAG, an Agentic RAG framework that exposes hierarchical retrieval interfaces directly to the model.<n>A-RAG provides three retrieval tools: keyword search, semantic search, and chunk read, enabling the agent to adaptively search and retrieve information across multiple granularities.<n> Experiments on multiple open-domain QA benchmarks show that A-RAG consistently outperforms existing approaches with comparable or lower retrieved tokens.
  arXiv  Detail & Related papers  (2026-02-03T12:07:21Z)
• SMc2f: Robust Scenario Mining for Robotic Autonomy from Coarse to Fine [8.662817298688147]
  RefAV is an end-to-end framework that uses large language models (LLMs) to spatially and temporally localize scenarios.<n>SMc2f is a pipeline that employs vision-language models (VLMs) for coarse image-text filtering.<n> Experiments on public datasets demonstrate substantial gains in both retrieval quality and efficiency.
  arXiv  Detail & Related papers  (2026-01-17T11:25:55Z)
• Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey [92.71325249013535]
  Deliberative tree search is a cornerstone of Large Language Model (LLM) research.<n>This paper introduces a unified framework that deconstructs search algorithms into three core components.
  arXiv  Detail & Related papers  (2025-10-11T03:29:18Z)
• Retrieval-augmented reasoning with lean language models [5.615564811138556]
  We develop a retrieval augmented conversational agent capable of interpreting complex, domain-specific queries.<n>Our system integrates a dense retriever with fine-tuned Qwen2.5-Instruct models.<n>All implementation details and code are publicly released to support and adaptation across domains.
  arXiv  Detail & Related papers  (2025-08-15T10:38:15Z)
• ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks [64.86209459039313]
  ThinkGeo is an agentic benchmark designed to evaluate tool-augmented agents on remote sensing tasks via structured tool use and multi-step planning.<n>We implement a ReAct-style interaction loop and evaluate both open and closed-source LLMs on 486 structured agentic tasks with 1,773 expert-verified reasoning steps.<n>Our analysis reveals notable disparities in tool accuracy and planning consistency across models.
  arXiv  Detail & Related papers  (2025-05-29T17:59:38Z)
• Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning [62.640169289390535]
  SPLIT-RAG is a multi-agent RAG framework that addresses the limitations with question-driven semantic graph partitioning and collaborative subgraph retrieval.<n>The innovative framework first create Semantic Partitioning of Linked Information, then use the Type-Specialized knowledge base to achieve Multi-Agent RAG.<n>The attribute-aware graph segmentation manages to divide knowledge graphs into semantically coherent subgraphs, ensuring subgraphs align with different query types.<n>A hierarchical merging module resolves inconsistencies across subgraph-derived answers through logical verifications.
  arXiv  Detail & Related papers  (2025-05-20T06:44:34Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• Task-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AI [108.08079323459822]
  This paper studies a new multi-intelligent edge artificial-latency (AI) system, which jointly exploits the AI model split inference and integrated sensing and communication (ISAC) We measure the inference accuracy by adopting an approximate but tractable metric, namely discriminant gain.
  arXiv  Detail & Related papers  (2022-07-03T06:57:07Z)

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.