Large language models (LLMs) have shown remarkable progress in code
generation, but their generated code often suffers from inefficiency, resulting
in longer execution times and higher memory consumption. To address this issue,
we propose Self Optimization based on OverheAd Profile (SOAP), a
self-optimization framework that utilizes execution overhead profiles to
improve the efficiency of LLM-generated code. SOAP first generates code using
an LLM, then executes it locally to capture execution time and memory usage
profiles. These profiles are fed back to the LLM, which then revises the code
to reduce overhead. To evaluate the effectiveness of SOAP, we conduct extensive
experiments on the EffiBench, HumanEval, and MBPP with 16 open-source and 6
closed-source models. Our evaluation results demonstrate that through iterative
self-optimization, SOAP significantly enhances the efficiency of LLM-generated
code. For example, the execution time (ET) of StarCoder2-15B for the EffiBench
decreases from 0.93 (s) to 0.12 (s) which reduces 87.1% execution time
requirement compared with the initial code. The total memory usage (TMU) of
StarCoder2-15B also decreases from 22.02 (Mb*s) to 2.03 (Mb*s), which decreases
90.8% total memory consumption during the execution process. The source code of
SOAP was released in this https URL

基于执行开销概要的自优化框架（SOAP）通过迭代的自优化显著提高大语言模型（LLM）生成的代码的效率。

通过自我优化提升生成代码的效率

SOAP: Enhancing Efficiency of Generated Code via Self-Optimization

The emergence of large language models (LLMs) has substantially influenced
natural language processing, demonstrating exceptional results across various
tasks. In this study, we employ ``Introspective Tips" to facilitate LLMs in
self-optimizing their decision-making. By introspectively examining
trajectories, LLM refines its policy by generating succinct and valuable tips.
Our method enhances the agent's performance in both few-shot and zero-shot
learning situations by considering three essential scenarios: learning from the
agent's past experiences, integrating expert demonstrations, and generalizing
across diverse games. Importantly, we accomplish these improvements without
fine-tuning the LLM parameters; rather, we adjust the prompt to generalize
insights from the three aforementioned situations. Our framework not only
supports but also emphasizes the advantage of employing LLM in in-contxt
decision-making. Experiments involving over 100 games in TextWorld illustrate
the superior performance of our approach.

本研究利用自省式提示 (Introspective Tips) 促进了大型语言模型 (Large Language Models) 的自我优化，从学习过程中的经验、集成专家演示和跨越多种游戏等三种方面提高决策性能，却不调整 LMM 参数，结论在 TextWorld 超过 100 个游戏中都表现出优异的结果。

自省提示：用于上下文决策的大型语言模型

Introspective Tips: Large Language Model for In-Context Decision Making

This article presents a new design for autonomous artificial intelligence
(AI), based on the state-of-the-art algorithms, and describes a new autonomous
AI system called AutoAI. The methodology is used to assemble the design founded
on self-improved algorithms that use new and emerging sources of data (NEFD).
The objective of the article is to conceptualise the design of a novel AutoAI
algorithm. The conceptual approach is used to advance into building new and
improved algorithms. The article integrates and consolidates the findings from
existing literature and advances the AutoAI design into (1) using new and
emerging sources of data for teaching and training AI algorithms and (2)
enabling AI algorithms to use automated tools for training new and improved
algorithms. This approach is going beyond the state-of-the-art in AI algorithms
and suggests a design that enables autonomous algorithms to self-optimise and
self-adapt, and on a higher level, be capable to self-procreate.

本文介绍了一种基于最先进算法的自主人工智能新设计，旨在用新兴数据源 (NERD) 的应用拼凑自我优化算法的新自主人工智能系统 AutoAI，这种方法超越了人工智能的现有水平，使自主算法能够自我优化和自适应，在更高层次上，能够自我繁殖。

自主人工智能现状综述

Review of the state of the art in autonomous artificial intelligence

Recently, there has been tremendous efforts by network operators and
equipment vendors to adopt intelligence and openness in the next generation
radio access network (RAN). The goal is to reach a RAN that can self-optimize
in a highly complex setting with multiple platforms, technologies and vendors
in a converged compute and connect architecture. In this paper, we propose two
nested actor-critic learning based techniques to optimize the placement of
resource allocation function, and as well, the decisions for resource
allocation. By this, we investigate the impact of observability on the
performance of the reinforcement learning based resource allocation. We show
that when a network function (NF) is dynamically relocated based on service
requirements, using reinforcement learning techniques, latency and throughput
gains are obtained.

本文提出两种基于 actor-critic 学习的技术来优化资源分配功能的位置以及资源分配决策，并研究了增强学习资源分配在可观测性方面对性能的影响，实验表明，在动态地网络功能（NF）根据服务要求进行重新定位时，使用强化学习技术能够获得延迟和吞吐量的提高。