ConceptARC at Scale: Studying Conceptual Understanding in Reasoning Models
cs.AI, cs.LG
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/mainlp/conceptarc-100-eval
Project page: https://mainlp.github.io/conceptarc100-project-page
Terminology
Sources
- Phi-4-reasoning Technical Report
- Distinguishing Performance From Competence in Evaluations of Humanlike Abstract Reasoning
- I-RAVEN-X: Benchmarking Generalization and Robustness of Analogical and Mathematical Reasoning in Large Language and Reasoning Models
- On the Measure of Intelligence
- Addressing the Abstraction and Reasoning Corpus via Procedural Example Generation
- Less is More: Recursive Reasoning with Tiny Networks
- Fluid Reasoning Representations
- ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus
- gpt-oss-120b & gpt-oss-20b Model Card
- Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction
- Gemma 4 Technical Report
- Qwen3 Technical Report
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents