UltraLogic: Enhancing LLM Reasoning through Large-Scale Data Synthesis and Bipolar Float Reward

• URL: http://arxiv.org/abs/2601.03205v1
• Date: Tue, 06 Jan 2026 17:41:32 GMT
• Title: UltraLogic: Enhancing LLM Reasoning through Large-Scale Data Synthesis and Bipolar Float Reward
• Abstract summary: We propose UltraLogic, a framework that decouples the logical core of a problem from its natural language expression.<n>The framework comprises hundreds of unique task types and an automated calibration pipeline across ten difficulty levels.
• Score: 12.686812126754404
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Large Language Models (LLMs) have demonstrated significant potential in natural language processing , complex general-purpose reasoning requiring multi-step logic, planning, and verification remains a critical bottleneck. Although Reinforcement Learning with Verifiable Rewards (RLVR) has succeeded in specific domains , the field lacks large-scale, high-quality, and difficulty-calibrated data for general reasoning. To address this, we propose UltraLogic, a framework that decouples the logical core of a problem from its natural language expression through a Code-based Solving methodology to automate high-quality data production. The framework comprises hundreds of unique task types and an automated calibration pipeline across ten difficulty levels. Furthermore, to mitigate binary reward sparsity and the Non-negative Reward Trap, we introduce the Bipolar Float Reward (BFR) mechanism, utilizing graded penalties to effectively distinguish perfect responses from those with logical flaws. Our experiments demonstrate that task diversity is the primary driver for reasoning enhancement , and that BFR, combined with a difficulty matching strategy, significantly improves training efficiency, guiding models toward global logical optima.

Related papers

• Stratified Consistency Distillation for Natural Language Formalization [8.652179594076536]
  We propose a fine-tuning-based Stratified Consistency Distillation approach to improve logical translation accuracy.<n>Our experiments show significant and consistent improvements in both Pass@K and our novel Equivalent Logical Similarity metrics.
  arXiv  Detail & Related papers  (2026-08-31T05:08:08Z)
• Unified Data Selection for LLM Reasoning [66.0118347918729]
  Training Large Language Models (LLMs) for complex, long-CoT reasoning is often bottlenecked by the need for massive high-quality reasoning data.<n>We propose High-Entropy Sum (HES), a training-free metric that quantifies reasoning quality by summing only the entropy of the top (e.g., 0.5%) highest-entropy tokens in each reasoning sample.
  arXiv  Detail & Related papers  (2026-05-21T12:21:41Z)
• Unlocking Biological Workflows for Robust Protein-Text Question Answering: A Dual-Dimensional RAG Framework [60.82334952881798]
  Protein-Text Question Answering (QA) is crucial for interpreting biological sequences through natural language.<n>We propose 2D-ProteinRAG, a novel framework that empowers Large Language Models (LLMs) to operate within the gold-standard biological research workflow.<n>We show that 2D-Protein consistently achieves state-of-the-art performance, outperforming fine-tuned baselines and other RAG methods.
  arXiv  Detail & Related papers  (2026-05-17T05:03:24Z)
• Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective [85.06838178922791]
  Reinforcement Learning (RL) has proven highly effective for autoregressive language models.<n>But adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges.<n>We propose a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy.
  arXiv  Detail & Related papers  (2025-12-03T13:05:32Z)
• Making Mathematical Reasoning Adaptive [61.45161826629692]
  We propose the AdaR framework to enable adaptive reasoning in large language models (LLMs)<n>AdaR synthesizes logically equivalent queries by varying variable values, and trains models with RLVR on these data to penalize spurious logic.<n> Experimental results demonstrate that AdaR improves robustness and generalization, achieving substantial improvement in mathematical reasoning.
  arXiv  Detail & Related papers  (2025-10-06T09:30:05Z)
• Unlocking Symbol-Level Precoding Efficiency Through Tensor Equivariant Neural Network [84.22115118596741]
  We propose an end-to-end deep learning (DL) framework with low inference complexity for symbol-level precoding.<n>We show that the proposed framework captures substantial performance gains of optimal SLP, while achieving an approximately 80-times speedup over conventional methods.
  arXiv  Detail & Related papers  (2025-10-02T15:15:50Z)
• RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning [27.235259453535537]
  RationAnomaly is a novel framework that enhances log anomaly detection by synergizing Chain-of-Thought fine-tuning with reinforcement learning.<n>We have released the corresponding resources, including code and datasets.
  arXiv  Detail & Related papers  (2025-09-18T07:35:58Z)
• Do LLMs Dream of Discrete Algorithms? [0.7646713951724011]
  Large Language Models (LLMs) have rapidly transformed the landscape of artificial intelligence.<n>Their reliance on probabilistic inference limits their effectiveness in domains requiring strict logical reasoning.<n>This paper proposes a neurosymbolic approach that augments LLMs with logic-based reasoning modules.
  arXiv  Detail & Related papers  (2025-06-29T22:03:01Z)
• Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation [24.081573908824353]
  First-order logic (FOL) reasoning is pivotal for intelligent systems.<n>Existing benchmarks often rely on extensive human annotation or handcrafted templates.<n>We propose a novel framework called ProverGen that synergizes the generative strengths of Large Language Models with the rigor and precision of symbolic provers.
  arXiv  Detail & Related papers  (2025-02-10T15:31:54Z)
• ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning [92.76959707441954]
  We introduce ZebraLogic, a comprehensive evaluation framework for assessing LLM reasoning performance.<n>ZebraLogic enables the generation of puzzles with controllable and quantifiable complexity.<n>Our results reveal a significant decline in accuracy as problem complexity grows.
  arXiv  Detail & Related papers  (2025-02-03T06:44:49Z)
• MTLSO: A Multi-Task Learning Approach for Logic Synthesis Optimization [19.13500546022262]
  MTLSO is a Multi-Task Learning approach for Logic Synthesis Optimization. We introduce an auxiliary task of binary multi-label graph classification alongside the primary regression task. We also employ a hierarchical graph representation learning strategy to improve the model's capacity for learning expressive graph-level representations.
  arXiv  Detail & Related papers  (2024-09-09T21:20:36Z)
• Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-loop and Hessian-free Solution Strategy [45.982542530484274]
  Large-scale non Bi-Level (BLO) problems are increasingly applied in machine learning. These challenges involve ensuring computational efficiency and providing theoretical guarantees.
  arXiv  Detail & Related papers  (2024-05-16T09:33:28Z)
• 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)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)

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.