Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Combining Deep Learning and Qualitative Spatial Reasoning to Learn Complex Structures from Sparse Examples with Noise
Nikhil Krishnaswamy, Scott Friedman, James Pustejovsky
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use graph matching to choose moves by maximal common subgraph similarity | Structure-learning and generation system · Generated staircase structures | average evaluator score: 2.0375 -> 5.8313 | Improved |
| Use Jaccard distance to select moves instead of random choice | Structure-learning and generation system · Generated staircase structures | average evaluator score: 2.0375 -> 4.3375 | Improved |
| Use Levenshtein distance to select moves instead of random choice | Structure-learning and generation system · Generated staircase structures | average evaluator score: 2.0375 -> 3.7688 | Improved |
| Prune move options with Levenshtein distance before graph matching | Spire graph matching · Generated staircase structures | average evaluator score: 5.8313 -> 4.7188 | Hurt |
Closest papers by meaning
- Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models (ICML 2026 · similarity 0.84)
- Thinking in Structures: Evaluating Spatial Intelligence in Constraint-Governed Spaces (ICML 2026 · similarity 0.84)
- Geometrically-Constrained Agent for Spatial Reasoning (CVPR 2026 · similarity 0.84)
- SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning (NeurIPS 2026 · similarity 0.84)
- Reasoning in Visual Navigation of End-to-end Trained Agents: A Dynamical Systems Approach (CVPR 2025 · similarity 0.84)
- No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers (ICLR 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
