OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization

• URL: http://arxiv.org/abs/2506.18880v1
• Date: Mon, 23 Jun 2025 17:51:40 GMT
• Title: OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization
• Authors: Yiyou Sun, Shawn Hu, Georgia Zhou, Ken Zheng, Hannaneh Hajishirzi, Nouha Dziri, Dawn Song,
• Abstract summary: Recent large-scale language models (LLMs) with long Chain-of-such reasoning as DeepSeek-R1-have achieved impressive results on Olympiad-level mathematics.<n>We introduce OMEGA-Out-of-distribution Math Problems Evaluation with 3 Generalization Axes-a benchmark designed to evaluate three axes of out-of-distribution generalization.
• Score: 88.76091817642963
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent large-scale language models (LLMs) with long Chain-of-Thought reasoning-such as DeepSeek-R1-have achieved impressive results on Olympiad-level mathematics benchmarks. However, they often rely on a narrow set of strategies and struggle with problems that require a novel way of thinking. To systematically investigate these limitations, we introduce OMEGA-Out-of-distribution Math Problems Evaluation with 3 Generalization Axes-a controlled yet diverse benchmark designed to evaluate three axes of out-of-distribution generalization, inspired by Boden's typology of creativity: (1) Exploratory-applying known problem solving skills to more complex instances within the same problem domain; (2) Compositional-combining distinct reasoning skills, previously learned in isolation, to solve novel problems that require integrating these skills in new and coherent ways; and (3) Transformative-adopting novel, often unconventional strategies by moving beyond familiar approaches to solve problems more effectively. OMEGA consists of programmatically generated training-test pairs derived from templated problem generators across geometry, number theory, algebra, combinatorics, logic, and puzzles, with solutions verified using symbolic, numerical, or graphical methods. We evaluate frontier (or top-tier) LLMs and observe sharp performance degradation as problem complexity increases. Moreover, we fine-tune the Qwen-series models across all generalization settings and observe notable improvements in exploratory generalization, while compositional generalization remains limited and transformative reasoning shows little to no improvement. By isolating and quantifying these fine-grained failures, OMEGA lays the groundwork for advancing LLMs toward genuine mathematical creativity beyond mechanical proficiency.

Related papers

• LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning [29.047063129464494]
  Large language models (LLMs) excel at many supervised tasks but often struggle with structured reasoning unfamiliar settings.<n>This discrepancy suggests that standard fine-tuning pipelines may instill narrow, domain-specifics rather than fostering general-purpose thinking strategies.<n>We propose a "play to learn" framework that fine-tunes LLMs through reinforcement learning on a suite of seven custom logic puzzles.
  arXiv  Detail & Related papers  (2025-06-05T09:40:47Z)
• Computational Thinking Reasoning in Large Language Models [69.28428524878885]
  Computational Thinking Model (CTM) is a novel framework that incorporates computational thinking paradigms into large language models (LLMs)<n>Live code execution is seamlessly integrated into the reasoning process, allowing CTM to think by computing.<n>CTM outperforms conventional reasoning models and tool-augmented baselines in terms of accuracy, interpretability, and generalizability.
  arXiv  Detail & Related papers  (2025-06-03T09:11:15Z)
• Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models [86.45058529521258]
  OlymMATH is a novel Olympiad-level mathematical benchmark designed to rigorously test the complex reasoning capabilities of LLMs.<n>OlymMATH features 200 meticulously curated problems, each manually verified and available in parallel English and Chinese versions.
  arXiv  Detail & Related papers  (2025-03-27T11:20:17Z)
• Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving [32.293348354802504]
  Large language models (LLMs) have demonstrated transformative potential across various domains.<n>Retrieval-Augmented Generation (RAG) has emerged as a promising solution to enhance LLMs accuracy.<n>We propose CogGRAG, a cognition inspired graph-based RAG framework.
  arXiv  Detail & Related papers  (2025-03-09T11:50:39Z)
• PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models [59.920971312822736]
  We introduce PromptCoT, a novel approach for automatically generating high-quality Olympiad-level math problems.<n>The proposed method synthesizes complex problems based on mathematical concepts and the rationale behind problem construction.<n>Our method is evaluated on standard benchmarks including GSM8K, MATH-500, and AIME2024, where it consistently outperforms existing problem generation methods.
  arXiv  Detail & Related papers  (2025-03-04T06:32:30Z)
• Large Language Models and Mathematical Reasoning Failures [1.6114012813668932]
  This paper investigates the mathematical reasoning capabilities of large language models (LLMs) using 50 newly constructed high-school-level word problems.<n>We rigorously analyze both final answers and solution steps to identify reasoning failures.<n>We find that while newer models (e.g., o3-mini, deepseek-r1) achieve higher accuracy, all models exhibit errors in spatial reasoning, strategic planning, and arithmetic.
  arXiv  Detail & Related papers  (2025-02-17T09:07:32Z)
• Bridging Visualization and Optimization: Multimodal Large Language Models on Graph-Structured Combinatorial Optimization [56.17811386955609]
  Graph-structured challenges are inherently difficult due to their nonlinear and intricate nature.<n>In this study, we propose transforming graphs into images to preserve their higher-order structural features accurately.<n>By combining the innovative paradigm powered by multimodal large language models with simple search techniques, we aim to develop a novel and effective framework.
  arXiv  Detail & Related papers  (2025-01-21T08:28:10Z)
• Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning [30.40415945003794]
  We investigate the compositionality of large language models (LLMs) in mathematical reasoning. Since problems with logical flaws are quite rare in the real world, these represent "unseen" cases to LLMs. Our experiments show that while LLMs possess both components of requisite knowledge, they do not textbfspontaneously combine them to handle these novel cases.
  arXiv  Detail & Related papers  (2024-05-05T16:35:30Z)
• A Neural Rewriting System to Solve Algorithmic Problems [47.129504708849446]
  We propose a modular architecture designed to learn a general procedure for solving nested mathematical formulas. Inspired by rewriting systems, a classic framework in symbolic artificial intelligence, we include in the architecture three specialized and interacting modules. We benchmark our system against the Neural Data Router, a recent model specialized for systematic generalization, and a state-of-the-art large language model (GPT-4) probed with advanced prompting strategies.
  arXiv  Detail & Related papers  (2024-02-27T10:57:07Z)
• Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions [47.83142414018448]
  We focus on two popular reasoning tasks: arithmetic reasoning and code generation. We introduce (i) a general ontology of perturbations for math and coding questions, (ii) a semi-automatic method to apply these perturbations, and (iii) two datasets. We show a significant performance drop across all the models against perturbed questions.
  arXiv  Detail & Related papers  (2024-01-17T18:13:07Z)
• Faith and Fate: Limits of Transformers on Compositionality [109.79516190693415]
  We investigate the limits of transformer large language models across three representative compositional tasks. These tasks require breaking problems down into sub-steps and synthesizing these steps into a precise answer. Our empirical findings suggest that transformer LLMs solve compositional tasks by reducing multi-step compositional reasoning into linearized subgraph matching.
  arXiv  Detail & Related papers  (2023-05-29T23:24:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.