Self-Evolving Neuro-Symbolic Skills for Tool-Augmented Spatial Reasoning
Shi-Yu Tian, Zhuo-Xia Wang, Xuan-Yi Zhu, Zhi Zhou, Xinwei Yang, Kun-Yang Yu, Ming Yang, Yang Chen, Yu-Feng Li
cs.AI
Submitted: 2026-08-08
Updated: 2026-08-11
Comments: 25 pages, 9 figures, 10 tables; includes supplementary material
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large vision-language models have achieved strong performance in multimodal reasoning, but they remain unreliable on fine-grained spatial tasks that demand both precise spatial perception and
Terminology
Abstract
Large vision-language models have achieved strong performance in multimodal reasoning, but they remain unreliable on fine-grained spatial tasks that demand both precise spatial perception and fine-grained geometric computation beyond end-to-end generation. Tool augmentation offers a natural solution, while existing methods either plan tool calls from scratch without explicit dependency constraints or rely on fixed pipelines that are redundant and generalize poorly across spatial tasks. An effective spatial reasoning agent should instead accumulate reusable experience and adaptively compose it for new problems. To this end, we propose NeSy-Spatial, a neuro-symbolic framework for self-evolving spatial skills. NeSy-Spatial abstracts tool interactions and geometric operations into typed executable atomic instructions and composes them into two complementary skill types: Tool-Use Skills for organizing tool execution and Geometry Skills for structured geometric reasoning. During inference, NeSy-Spatial retrieves and executes relevant skills in a closed-loop process. During evolution, it analyzes buffered successful and failed trajectories to refine skill structures and prune unreliable or inactive entries. Experiments on three spatial reasoning benchmarks show that NeSy-Spatial consistently improves reasoning accuracy with more precise tool utilization.
Sources
- SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models
- SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL
- Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
- SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
- TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics
- OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models
- ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models
- STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?
- LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Inducing Programmatic Skills for Agentic Tasks
- Agent Workflow Memory
- Depth Anything V2
- MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence
- Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoning
- Thyme: Think Beyond Images
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems