Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL
On the map: LLM reasoning → Reinforcement learning for reasoning
Abstract (arXiv)
This paper demonstrates that model-based reinforcement learning (model-based RL) is a suitable approach for the task of analogical reasoning. We hypothesize that model-based RL can solve analogical reasoning tasks more efficiently through the creation of internal models. To test this, we compared DreamerV3, a model-based RL method, with Proximal Policy Optimization, a model-free RL method, on the Abstraction and Reasoning Corpus (ARC) tasks. Our results indicate that model-based RL not only outperforms model-free RL in learning and generalizing from single tasks but also shows significant advantages in reasoning across similar tasks.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning. Builds on 20 of its 27 references that are in the map. First posted on arXiv 27 Aug 2024.
Builds on
20 of 27 references.
Closest ancestors · 1
Same direction, newest first
- 2017Proximal Policy Optimization Algorithms20 Jul
Other references · 19
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2018World Modelscited by 1,444
- 2023Mastering Diverse Domains through World Modelscited by 1,193
- 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
- 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
- 2023Large Language Models as General Pattern Machinescited by 196
- 2017Imagination-Augmented Agents for Deep Reinforcement Learningcited by 137
- 2021Fast and flexible: Human program induction in abstract reasoning taskscited by 33
- 2022A Review of Emerging Research Directions in Abstract Visual Reasoningcited by 33
- 2024Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpuscited by 32
7 more
- 2021Neural-guided, Bidirectional Program Search for Abstraction and Reasoningcited by 23
- 2024CodeIt: Self-Improving Language Models with Prioritized Hindsight Replaycited by 23
- 2024Neural networks for abstraction and reasoning: Towards broad generalization in machinescited by 13
- 2023Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformercited by 12
- 2023Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) Challengecited by 11
- 2023A Neurodiversity-Inspired Solver for the Abstraction & Reasoning Corpus (ARC) Using Visual Imagery and Program Synthesiscited by 9
- 2024ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learningcited by 7
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025A Survey of Reinforcement Learning for Large Reasoning Models
- 2025Demystifying Reinforcement Learning in Agentic Reasoning
- 2025Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
- 2025Reshaping Reasoning in LLMs: A Theoretical Analysis of RL Training Dynamics through Pattern Selection
- 2025Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
- 2026RL with Learnable Textual Feedback: A Bilevel Approach
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- 2025Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models