From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark
cs.AI, cs.CL
Submitted: 2025-05-23
Updated: 2026-09-26
Comments: This paper is accepted at EMNLP 2026 Main
Code: https://github.com/da-fr/arc-prize-2024
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- On the Measure of Intelligence
- Evaluating Large Language Models Trained on Code
- Planning-Driven Programming: A Large Language Model Programming Workflow
- Program Synthesis with Large Language Models
- Evaluation of OpenAI o1: Opportunities and Challenges of AGI
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Can LLM be a Good Path Planner based on Prompt Engineering? Mitigating the Hallucination for Path Planning
- LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations
- H-ARC: A Robust Estimate of Human Performance on the Abstraction and Reasoning Corpus Benchmark
- Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs
- Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects
- Visual question answering: from early developments to recent advances -- a survey
- 1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation
- An Approach to Solving the Abstraction and Reasoning Corpus (ARC) Challenge
- Addressing the Abstraction and Reasoning Corpus via Procedural Example Generation
- The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain
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