# Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models

arXiv: https://arxiv.org/abs/2602.08658 · HTML: https://mlsanity.com/paper/2602.08658/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 15 of its 47 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 15 of 15)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [OpenThoughts: Data Recipes for Reasoning Models](https://mlsanity.com/paper/2506.04178/) (2025)
- [Olmo 3](https://mlsanity.com/paper/2512.13961/) (2025)
- [Datasets for Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2402.18041/) (2024)
- [FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training](https://mlsanity.com/paper/2501.09213/) (2025)
- [Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models](https://mlsanity.com/paper/2505.10554/) (2025)
- [The Bayesian Geometry of Transformer Attention](https://mlsanity.com/paper/2512.22471/) (2025)
- [Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi](https://mlsanity.com/paper/2504.06011/) (2025)
- [Agentar-DeepFinance-100K: A Large-Scale Financial Dataset via Systematic Chain-of-Thought Synthesis Optimization](https://mlsanity.com/paper/2507.12901/) (2025)
- [Reasoning Scaffolding: Distilling the Flow of Thought from LLMs](https://mlsanity.com/paper/2509.23619/) (2025)
- [Optimal Transport Depth Up-Scaling](https://mlsanity.com/paper/2508.08011/) (2025)
- [Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian](https://mlsanity.com/paper/2509.05668/) (2025)
- [Expanding Foundational Language Capabilities in Open-Source LLMs through a Korean Case Study](https://mlsanity.com/paper/2509.03972/) (2025)

## Built on by (most cited first, 3 of 3)

- [Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility](https://mlsanity.com/paper/2608.03930/) (2026)
- [Compliance vs. Sensibility: On the Reasoning Controllability in Large Language Models](https://mlsanity.com/paper/2604.27251/) (2026)
- [Evaluating Multi-Dimensional Generalization of Large Language Models in Temporal Extraction Tasks](https://mlsanity.com/paper/2610.02549/) (2026)

## Abstract (arXiv)

Deduction, induction, and abduction are fundamental reasoning paradigms, core for human logical thinking. Although improving Large Language Model (LLM) reasoning has attracted significant research efforts, the extent to which the fundamental paradigms induce generalization has yet to be systematically explored. In this study, we shed light on how the interplay between these core paradigms influences LLMs' reasoning behavior. To this end, we first collect a new dataset of reasoning trajectories from symbolic tasks, each targeting one of the three fundamental paradigms, to abstract from concrete world knowledge. Then, we investigate effective ways for inducing these skills into LLMs. We experiment with a battery of methods including simple fine-tuning, and more complex approaches to increase model depth, or transform a dense model to a mixture-of-experts. We comprehensively evaluate induced models on realistic out-of-domain tasks, that are entirely formulated in natural language and contain real-world knowledge. Our results reveal that our approach yields strong generalizability with substantial performance gains (up to 14.60) across realistic tasks.