Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles

• URL: http://arxiv.org/abs/2505.19914v2
• Date: Mon, 09 Jun 2025 07:49:32 GMT
• Title: Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
• Authors: Jiangjie Chen, Qianyu He, Siyu Yuan, Aili Chen, Zhicheng Cai, Weinan Dai, Hongli Yu, Qiying Yu, Xuefeng Li, Jiaze Chen, Hao Zhou, Mingxuan Wang,
• Abstract summary: We introduce Enigmata, the first comprehensive suite tailored for improving Large Language Models with puzzle reasoning skills.<n>It includes 36 tasks across seven categories, each with 1) a generator that produces unlimited examples with controllable difficulty and 2) a rule-based verifier for automatic evaluation.<n>Our trained model, Qwen2.5-32B-Enigmata, consistently surpasses o3-mini-high and o1 on the puzzle reasoning benchmarks.
• Score: 46.71887319140096
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Models (LLMs), such as OpenAI's o1 and DeepSeek's R1, excel at advanced reasoning tasks like math and coding via Reinforcement Learning with Verifiable Rewards (RLVR), but still struggle with puzzles solvable by humans without domain knowledge. We introduce Enigmata, the first comprehensive suite tailored for improving LLMs with puzzle reasoning skills. It includes 36 tasks across seven categories, each with 1) a generator that produces unlimited examples with controllable difficulty and 2) a rule-based verifier for automatic evaluation. This generator-verifier design supports scalable, multi-task RL training, fine-grained analysis, and seamless RLVR integration. We further propose Enigmata-Eval, a rigorous benchmark, and develop optimized multi-task RLVR strategies. Our trained model, Qwen2.5-32B-Enigmata, consistently surpasses o3-mini-high and o1 on the puzzle reasoning benchmarks like Enigmata-Eval, ARC-AGI (32.8%), and ARC-AGI 2 (0.6%). It also generalizes well to out-of-domain puzzle benchmarks and mathematical reasoning, with little multi-tasking trade-off. When trained on larger models like Seed1.5-Thinking (20B activated parameters and 200B total parameters), puzzle data from Enigmata further boosts SoTA performance on advanced math and STEM reasoning tasks such as AIME (2024-2025), BeyondAIME and GPQA (Diamond), showing nice generalization benefits of Enigmata. This work offers a unified, controllable framework for advancing logical reasoning in LLMs. Resources of this work can be found at https://seed-enigmata.github.io.

Related papers

• Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code [76.80306464249217]
  We propose TeaR, which aims at teaching LLMs to reason better.<n>TeaR leverages careful data curation and reinforcement learning to guide models in discovering optimal reasoning paths through code-related tasks.<n>We conduct extensive experiments using two base models and three long-CoT distillation models, with model sizes ranging from 1.5 billion to 32 billion parameters, and across 17 benchmarks spanning Math, Knowledge, Code, and Logical Reasoning.
  arXiv  Detail & Related papers  (2025-07-10T07:34:05Z)
• R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement Learning [14.208804782749793]
  We present R1-Code-Interpreter, an extension of a text-only Large Language Models (LLMs) trained via multi-turn supervised fine-tuning (SFT) and reinforcement learning (RL)<n>R1-Code-Interpreter autonomously generates multiple code queries during step-by-step reasoning.<n>Unlike prior RL work on narrow domains, we find that Code Interpreter training is significantly harder due to high task diversity and expensive code execution.
  arXiv  Detail & Related papers  (2025-05-27T18:47:33Z)
• Thinkless: LLM Learns When to Think [57.857534644932194]
  Reasoning Language Models, capable of extended chain-of-thought reasoning, have demonstrated remarkable performance on tasks requiring complex logical inference.<n>We propose Thinkless, a learnable framework that empowers an LLM to adaptively select between short-form and long-form reasoning.<n>On several benchmarks such as Minerva Algebra, MATH-500, and GSM8K, Thinkless is able to reduce the usage of long-chain thinking by 50% - 90%.
  arXiv  Detail & Related papers  (2025-05-19T17:24:16Z)
• Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning [66.43194385702297]
  Large Language Models (LLMs) have shown strong reasoning capabilities, particularly when enhanced through Reinforcement Learning (RL)<n>We propose NEMOTRON-CROSSTHINK, a framework that systematically incorporates multi-domain corpora, including both synthetic and real-world question-answer pairs, into RL training to improve generalization across diverse reasoning tasks.
  arXiv  Detail & Related papers  (2025-04-15T21:37:13Z)
• DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning [95.31714779585272]
  DeepMath-103K is a large-scale mathematical dataset designed with high difficulty (primarily levels 5-9)<n>It includes rigorous decontamination against numerous benchmarks, and verifiable answers for rule-based RL reward.<n>DeepMath-103K fosters the development of generalizable and advancing reasoning.
  arXiv  Detail & Related papers  (2025-04-15T17:59:51Z)
• FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving [90.88021670297664]
  FINEREASON is a logic-puzzle benchmark for evaluation of large language models' reasoning capabilities.<n>We introduce two tasks: state checking, and state transition, for a comprehensive evaluation of how models assess the current situation and plan the next move.<n>We show that models trained on our state checking and transition data demonstrate gains in math reasoning by up to 5.1% on GSM8K.
  arXiv  Detail & Related papers  (2025-02-27T16:23:25Z)
• Diverse Inference and Verification for Advanced Reasoning [19.88677753421871]
  Reasoning LLMs such as OpenAI o1, o3 and DeepSeek R1 have made significant progress in mathematics and coding.<n>We use a diverse inference approach that combines multiple models and methods at test time.<n>We find that verifying mathematics and code problems, and rejection sampling on other problems is simple and effective.
  arXiv  Detail & Related papers  (2025-02-14T07:22:25Z)
• The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles [29.214813685163218]
  Release of OpenAI's o-[n] series, such as o1, o3, and o4-mini, mark a significant paradigm shift in Large Language Models.<n>We track the evolution of the GPT-[n] and o-[n] series models on challenging multimodal puzzles.<n>Our results reveal that o-[n] series, particularly later iterations like o3 and o4-mini, significantly outperform the GPT-[n] series and show strong scalability in multimodal reasoning.
  arXiv  Detail & Related papers  (2025-02-03T05:47:04Z)
• Solving Zebra Puzzles Using Constraint-Guided Multi-Agent Systems [25.0042181817455]
  We introduce a multi-agent system, ZPS, that integrates Large Language Models with an off the shelf theorem prover. This system tackles the complex puzzle-solving task by breaking down the problem into smaller, manageable parts. We also introduce an automated grid puzzle grader to assess the correctness of our puzzle solutions and show that the automated grader is reliable by evaluating it in a user-study.
  arXiv  Detail & Related papers  (2024-07-04T14:22:25Z)
• Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning [89.89857766491475]
  We propose a curriculum-based logical-aware instruction tuning framework, named LACT.<n>Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition.<n> Experiments across widely used datasets demonstrate that LACT has substantial improvements(brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art.
  arXiv  Detail & Related papers  (2024-05-02T18:12:08Z)
• MasonTigers at SemEval-2024 Task 9: Solving Puzzles with an Ensemble of Chain-of-Thoughts [5.91695168183101]
  This paper presents team MasonTigers submission to the SemEval-2024 Task 9. It provides a dataset of puzzles for testing natural language understanding. We employ large language models (LLMs) to solve this task through several prompting techniques.
  arXiv  Detail & Related papers  (2024-03-22T06:31:49Z)
• Are Deep Neural Networks SMARTer than Second Graders? [85.60342335636341]
  We evaluate the abstraction, deduction, and generalization abilities of neural networks in solving visuo-linguistic puzzles designed for children in the 6--8 age group. Our dataset consists of 101 unique puzzles; each puzzle comprises a picture question, and their solution needs a mix of several elementary skills, including arithmetic, algebra, and spatial reasoning. Experiments reveal that while powerful deep models offer reasonable performances on puzzles in a supervised setting, they are not better than random accuracy when analyzed for generalization.
  arXiv  Detail & Related papers  (2022-12-20T04:33:32Z)

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.