Can Large Language Models Invent Algorithms to Improve Themselves?

• URL: http://arxiv.org/abs/2410.15639v2
• Date: Tue, 22 Oct 2024 03:14:46 GMT
• Title: Can Large Language Models Invent Algorithms to Improve Themselves?
• Authors: Yoichi Ishibashi, Taro Yano, Masafumi Oyamada,
• Abstract summary: Large Language Models (LLMs) have shown remarkable performance improvements and are rapidly gaining adoption in industry. We propose the Self-Developing framework, which enables LLMs to autonomously generate and learn model-improvement algorithms. In mathematical reasoning tasks, Self-Developing not only creates models that surpass the seed model but also consistently outperforms models created using human-designed algorithms.
• Score: 3.6117068575553595
• License:
• Abstract: Large Language Models (LLMs) have shown remarkable performance improvements and are rapidly gaining adoption in industry. However, the methods for improving LLMs are still designed by humans, which restricts the invention of new model-improving algorithms to human expertise and imagination. To address this, we propose the Self-Developing framework, which enables LLMs to autonomously generate and learn model-improvement algorithms. In this framework, the seed model generates, applies, and learns model-improving algorithms, continuously improving both the seed model and the algorithms themselves. In mathematical reasoning tasks, Self-Developing not only creates models that surpass the seed model but also consistently outperforms models created using human-designed algorithms. Additionally, these LLM-discovered algorithms demonstrate strong effectiveness, including transferability to out-of-domain models.

Related papers

• MLGym: A New Framework and Benchmark for Advancing AI Research Agents [51.9387884953294]
  We introduce Meta MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing large language models on AI research tasks. This is the first Gym environment for machine learning (ML) tasks, enabling research on reinforcement learning (RL) algorithms for training such agents. We evaluate a number of frontier large language models (LLMs) on our benchmarks such as Claude-3.5-Sonnet, Llama-3.1 405B, GPT-4o, o1-preview, and Gemini-1.5 Pro.
  arXiv  Detail & Related papers  (2025-02-20T12:28:23Z)
• Tensor Network Estimation of Distribution Algorithms [0.0]
  Methods integrating tensor networks into evolutionary optimization algorithms have appeared in the recent literature. We find that optimization performance of these methods is not related to the power of the generative model in a straightforward way. In light of this we find that adding an explicit mutation operator to the output of the generative model often improves optimization performance.
  arXiv  Detail & Related papers  (2024-12-27T18:22:47Z)
• MARS: Unleashing the Power of Variance Reduction for Training Large Models [56.47014540413659]
  We propose a unified training framework for deep neural networks. We introduce three instances of MARS that leverage preconditioned gradient optimization. Results indicate that the implementation of MARS consistently outperforms Adam.
  arXiv  Detail & Related papers  (2024-11-15T18:57:39Z)
• EVOLvE: Evaluating and Optimizing LLMs For Exploration [76.66831821738927]
  Large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty. We measure LLMs' (in)ability to make optimal decisions in bandits, a state-less reinforcement learning setting relevant to many applications. Motivated by the existence of optimal exploration algorithms, we propose efficient ways to integrate this algorithmic knowledge into LLMs.
  arXiv  Detail & Related papers  (2024-10-08T17:54:03Z)
• Large Language Models as Surrogate Models in Evolutionary Algorithms: A Preliminary Study [5.6787965501364335]
  Surrogate-assisted selection is a core step in evolutionary algorithms to solve expensive optimization problems. Traditionally, this has relied on conventional machine learning methods, leveraging historical evaluated evaluations to predict the performance of new solutions. In this work, we propose a novel surrogate model based purely on LLM inference capabilities, eliminating the need for training.
  arXiv  Detail & Related papers  (2024-06-15T15:54:00Z)
• LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics [0.023020018305241332]
  This paper introduces a novel Large Language Model Evolutionary Algorithm (LLaMEA) framework. Given a set of criteria and a task definition (the search space), LLaMEA iteratively generates, mutates and selects algorithms. We show how this framework can be used to generate novel black-box metaheuristic optimization algorithms automatically.
  arXiv  Detail & Related papers  (2024-05-30T15:10:59Z)
• Algorithm Evolution Using Large Language Model [18.03090066194074]
  We propose a novel approach called Evolution Algorithm using Large Language Model (AEL) AEL does algorithm-level evolution without model training. Human effort and requirements for domain knowledge can be significantly reduced.
  arXiv  Detail & Related papers  (2023-11-26T09:38:44Z)
• When to Update Your Model: Constrained Model-based Reinforcement Learning [50.74369835934703]
  We propose a novel and general theoretical scheme for a non-decreasing performance guarantee of model-based RL (MBRL) Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns.
  arXiv  Detail & Related papers  (2022-10-15T17:57:43Z)
• Evolving Reinforcement Learning Algorithms [186.62294652057062]
  We propose a method for meta-learning reinforcement learning algorithms. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. We highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games.
  arXiv  Detail & Related papers  (2021-01-08T18:55:07Z)
• Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning [93.1435980666675]
  We show how optimistic exploration can be easily combined with state-of-the-art reinforcement learning algorithms. Our experiments demonstrate that optimistic exploration significantly speeds-up learning when there are penalties on actions.
  arXiv  Detail & Related papers  (2020-06-15T18:37:38Z)

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.