Adaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model Reasoning

• URL: http://arxiv.org/abs/2310.01446v2
• Date: Mon, 23 Dec 2024 08:29:47 GMT
• Title: Adaptive-Solver Framework for Dynamic Strategy Selection in Large Language Model Reasoning
• Authors: Jianpeng Zhou, Wanjun Zhong, Yanlin Wang, Jiahai Wang,
• Abstract summary: Large Language Models (LLMs) demonstrate impressive ability in handling reasoning tasks.<n>Most LLM-based methods adopt a one-size-fits-all approach.<n>Inflexibility of these methods can bring unnecessary computational overhead or sub-optimal performance.
• Score: 31.643337118330944
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large Language Models (LLMs) demonstrate impressive ability in handling reasoning tasks. However, unlike humans who can instinctively adapt their problem-solving strategies to the complexity of task, most LLM-based methods adopt a one-size-fits-all approach. These methods employ consistent models, sample sizes, prompting methods and levels of problem decomposition, regardless of the problem complexity. The inflexibility of these methods can bring unnecessary computational overhead or sub-optimal performance. To address this limitation, we introduce an Adaptive-Solver (AS) framework tha dynamically adapts solving strategies to suit various problems, enabling the flexible allocation of test-time computational resources. The framework functions with two primary modules. The initial evaluation module assesses the reliability of the current solution using answer consistency. If the solution is deemed unreliable, the subsequent adaptation module comes into play. Within this module, various types of adaptation strategies are employed collaboratively. Through such dynamic and multi-faceted adaptations, our framework can help reduce computational consumption and improve performance. Experimental results from complex reasoning benchmarks reveal that our method can significantly reduce API costs (up to 85%) while maintaining original performance. Alternatively, it achieves up to 4.5% higher accuracy compared to the baselines at the same cost. The code and dataset are available at https://github.com/john1226966735/Adaptive-Solver.

Related papers

• PATS: Process-Level Adaptive Thinking Mode Switching [53.53401063490537]
  Current large-language models (LLMs) typically adopt a fixed reasoning strategy, either simple or complex, for all questions, regardless of their difficulty.<n>This neglect of variation in task and reasoning process complexity leads to an imbalance between performance and efficiency.<n>Existing methods attempt to implement training-free fast-slow thinking system switching to handle problems of varying difficulty, but are limited by coarse-grained solution-level strategy adjustments.<n>We propose a novel reasoning paradigm: Process-Level Adaptive Thinking Mode Switching (PATS), which enables LLMs to dynamically adjust their reasoning strategy based on the difficulty of each step, optimizing the balance between
  arXiv  Detail & Related papers  (2025-05-25T17:58:50Z)
• Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs [76.43407125275202]
  o1-like models can emulate human-like long-time thinking during inference. This paper presents the first comprehensive study on the prevalent issue of overthinking in these models. We propose strategies to mitigate overthinking, streamlining reasoning processes without compromising accuracy.
  arXiv  Detail & Related papers  (2024-12-30T18:55:12Z)
• Large Language Models for Combinatorial Optimization of Design Structure Matrix [4.513609458468522]
  Combinatorial optimization (CO) is essential for improving efficiency and performance in engineering applications. When it comes to real-world engineering problems, algorithms based on pure mathematical reasoning are limited and incapable to capture the contextual nuances necessary for optimization. This study explores the potential of Large Language Models (LLMs) in solving engineering CO problems by leveraging their reasoning power and contextual knowledge.
  arXiv  Detail & Related papers  (2024-11-19T15:39:51Z)
• Autoformulation of Mathematical Optimization Models Using LLMs [50.030647274271516]
  We develop an automated approach to creating optimization models from natural language descriptions for commercial solvers. We identify the three core challenges of autoformulation: (1) defining the vast, problem-dependent hypothesis space, (2) efficiently searching this space under uncertainty, and (3) evaluating formulation correctness.
  arXiv  Detail & Related papers  (2024-11-03T20:41:38Z)
• Closed-form merging of parameter-efficient modules for Federated Continual Learning [9.940242741914748]
  We introduce LoRM, an alternating optimization strategy that trains one LoRA matrix at a time. We apply our proposed methodology to Federated Class-Incremental Learning (FCIL) Our method demonstrates state-of-the-art performance across a range of FCIL scenarios.
  arXiv  Detail & Related papers  (2024-10-23T15:30:13Z)
• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning [56.273799410256075]
  The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
  arXiv  Detail & Related papers  (2024-10-03T18:12:29Z)
• Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models [16.16372459671255]
  Large Language Models (LLMs) typically generate outputs token by token using a fixed compute budget. We propose a novel framework that integrates smaller auxiliary modules within each Feed-Forward Network layer of the LLM. We show that trained routers operate differently from oracles and often yield suboptimal solutions.
  arXiv  Detail & Related papers  (2024-10-01T16:10:21Z)
• AQA: Adaptive Question Answering in a Society of LLMs via Contextual Multi-Armed Bandit [59.10281630985958]
  In question answering (QA), different questions can be effectively addressed with different answering strategies. We develop a dynamic method that adaptively selects the most suitable QA strategy for each question. Our experiments show that the proposed solution is viable for adaptive orchestration of a QA system with multiple modules.
  arXiv  Detail & Related papers  (2024-09-20T12:28:18Z)
• Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity [59.57065228857247]
  Retrieval-augmented Large Language Models (LLMs) have emerged as a promising approach to enhancing response accuracy in several tasks, such as Question-Answering (QA) We propose a novel adaptive QA framework, that can dynamically select the most suitable strategy for (retrieval-augmented) LLMs based on the query complexity. We validate our model on a set of open-domain QA datasets, covering multiple query complexities, and show that ours enhances the overall efficiency and accuracy of QA systems.
  arXiv  Detail & Related papers  (2024-03-21T13:52:30Z)
• Learning Constrained Optimization with Deep Augmented Lagrangian Methods [54.22290715244502]
  A machine learning (ML) model is trained to emulate a constrained optimization solver. This paper proposes an alternative approach, in which the ML model is trained to predict dual solution estimates directly. It enables an end-to-end training scheme is which the dual objective is as a loss function, and solution estimates toward primal feasibility, emulating a Dual Ascent method.
  arXiv  Detail & Related papers  (2024-03-06T04:43:22Z)
• Merging Multi-Task Models via Weight-Ensembling Mixture of Experts [64.94129594112557]
  Merging Transformer-based models trained on different tasks into a single unified model can execute all the tasks concurrently. Previous methods, exemplified by task arithmetic, have been proven to be both effective and scalable. We propose to merge most of the parameters while upscaling the Transformer layers to a weight-ensembling mixture of experts (MoE) module.
  arXiv  Detail & Related papers  (2024-02-01T08:58:57Z)
• Improving Large Language Model Fine-tuning for Solving Math Problems [20.417053742869403]
  A large gap exists between large language models' pass-at-one and pass-at-N performance in solving math problems. Using the challenging MATH dataset, we investigate three fine-tuning strategies. We design a fine-tuning recipe that yields approximately 58.8% accuracy on the MATH dataset with fine-tuned PaLM 2-L models.
  arXiv  Detail & Related papers  (2023-10-16T04:11:19Z)
• Reinforcement Learning Methods for Wordle: A POMDP/Adaptive Control Approach [0.3093890460224435]
  We address the solution of the popular Wordle puzzle, using new reinforcement learning methods. For the Wordle puzzle, they yield on-line solution strategies that are very close to optimal at relatively modest computational cost.
  arXiv  Detail & Related papers  (2022-11-15T03:46:41Z)
• Learning Adaptive Evolutionary Computation for Solving Multi-Objective Optimization Problems [3.3266268089678257]
  This paper proposes a framework that integrates MOEAs with adaptive parameter control using Deep Reinforcement Learning (DRL) The DRL policy is trained to adaptively set the values that dictate the intensity and probability of mutation for solutions during optimization. We show the learned policy is transferable, i.e., the policy trained on a simple benchmark problem can be directly applied to solve the complex warehouse optimization problem.
  arXiv  Detail & Related papers  (2022-11-01T22:08:34Z)
• Slimmable Domain Adaptation [112.19652651687402]
  We introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank. Our framework surpasses other competing approaches by a very large margin on multiple benchmarks.
  arXiv  Detail & Related papers  (2022-06-14T06:28:04Z)
• Meta-Learning with Neural Tangent Kernels [58.06951624702086]
  We propose the first meta-learning paradigm in the Reproducing Kernel Hilbert Space (RKHS) induced by the meta-model's Neural Tangent Kernel (NTK) Within this paradigm, we introduce two meta-learning algorithms, which no longer need a sub-optimal iterative inner-loop adaptation as in the MAML framework. We achieve this goal by 1) replacing the adaptation with a fast-adaptive regularizer in the RKHS; and 2) solving the adaptation analytically based on the NTK theory.
  arXiv  Detail & Related papers  (2021-02-07T20:53:23Z)
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation [64.91560451900125]
  State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results. Few-shot segmentation is proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information.
  arXiv  Detail & Related papers  (2020-08-04T10:41:32Z)
• Deep Unfolding Network for Image Super-Resolution [159.50726840791697]
  This paper proposes an end-to-end trainable unfolding network which leverages both learning-based methods and model-based methods. The proposed network inherits the flexibility of model-based methods to super-resolve blurry, noisy images for different scale factors via a single model.
  arXiv  Detail & Related papers  (2020-03-23T17:55:42Z)
• Optimizing Wireless Systems Using Unsupervised and Reinforced-Unsupervised Deep Learning [96.01176486957226]
  Resource allocation and transceivers in wireless networks are usually designed by solving optimization problems. In this article, we introduce unsupervised and reinforced-unsupervised learning frameworks for solving both variable and functional optimization problems.
  arXiv  Detail & Related papers  (2020-01-03T11:01:52Z)

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.