AI for Distributed Systems Design: Scalable Cloud Optimization Through Repeated LLMs Sampling And Simulators

• URL: http://arxiv.org/abs/2510.18897v1
• Date: Mon, 20 Oct 2025 16:10:24 GMT
• Title: AI for Distributed Systems Design: Scalable Cloud Optimization Through Repeated LLMs Sampling And Simulators
• Authors: Jacopo Tagliabue,
• Abstract summary: We explore AI-driven distributed-systems policy design by combining code generation from large language models with deterministic verification in a domain-specific simulator.<n>We report preliminary results on throughput improvements across multiple models.<n>We conjecture that AI will be crucial for scaling this methodology by helping to bootstrap new simulators.
• Score: 3.1594665317979698
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We explore AI-driven distributed-systems policy design by combining stochastic code generation from large language models (LLMs) with deterministic verification in a domain-specific simulator. Using a Function-as-a-Service runtime (Bauplan) and its open-source simulator (Eudoxia) as a case study, we frame scheduler design as an iterative generate-and-verify loop: an LLM proposes a Python policy, the simulator evaluates it on standardized traces, and structured feedback steers subsequent generations. This setup preserves interpretability while enabling targeted search over a large design space. We detail the system architecture and report preliminary results on throughput improvements across multiple models. Beyond early gains, we discuss the limits of the current setup and outline next steps; in particular, we conjecture that AI will be crucial for scaling this methodology by helping to bootstrap new simulators.

Related papers

• PymooLab: An Open-Source Visual Analytics Framework for Multi-Objective Optimization using LLM-Based Code Generation and MCDM [0.0]
  PymooLab is an open-source visual analytics environment built on top of textitpymoo.<n>It unifies configuration, execution monitoring, and formal decision support in a single reproducible workflow.<n>For computationally intensive studies, PymooLab relies on the native textitpymoo acceleration pathway through JAX.
  arXiv  Detail & Related papers  (2026-03-02T00:56:32Z)
• Model-Free Assessment of Simulator Fidelity via Quantile Curves [12.483260526189449]
  Simulation of complex systems originated in manufacturing and queuing applications. It is now widely used for large-scale, ML-based systems in research, education, and consumer surveys.<n>We propose a computationally tractable method to estimate the quantile function of the discrepancy between the simulated and ground-truth outcome distributions.
  arXiv  Detail & Related papers  (2025-12-04T17:39:51Z)
• Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios [76.85739138203014]
  We present SpecFormer, a novel architecture that accelerates unidirectional and attention mechanisms.<n>We demonstrate that SpecFormer achieves lower training demands and reduced computational costs.
  arXiv  Detail & Related papers  (2025-11-25T14:20:08Z)
• STAGE: A Symbolic Tensor grAph GEnerator for distributed AI system co-design [6.182971013882298]
  Symbolic(STAGE) is a framework that synthesizes high-fidelity execution traces to accurately model workload execution.<n>It supports a comprehensive set of parallelization strategies, allowing users to explore a wide spectrum of LLM architectures and system configurations.
  arXiv  Detail & Related papers  (2025-11-13T16:44:56Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• HEAS: Hierarchical Evolutionary Agent Simulation Framework for Cross-Scale Modeling and Multi-Objective Search [4.807104001943257]
  Hierarchical Simulation Agent (HEAS) is a Python framework that unifies layered agent-based modeling with evolutionary optimization and tournament evaluation.<n>HEAS represents models as hierarchies of lightweight processes ("streams") scheduled in deterministic layers that read and write a shared context.<n> compact API and CLI-simulate, optimize, evaluate-expose single- and multi-objective evolution.
  arXiv  Detail & Related papers  (2025-08-21T13:35:46Z)
• ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation [8.554484252096913]
  We present a framework for refining and customizing open- and closed-source large language models (LLMs)<n>We harness the power of AI in generating scripts that perform PyChrono virtual experiments.
  arXiv  Detail & Related papers  (2025-08-19T16:12:51Z)
• AI-driven Orchestration at Scale: Estimating Service Metrics on National-Wide Testbeds [0.1497962813548524]
  This paper proposes a large-scale validation method using a network slicing prediction model to forecast latency using Deep Neural Networks (DNNs) and basic ML algorithms embedded within an NS architecture.<n>It measures and compares the performance of different DNNs and ML algorithms, considering a distributed database application deployed as a network slice over two large-scale production testbeds.
  arXiv  Detail & Related papers  (2025-07-21T21:24:40Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback [52.763620660061115]
  ONI is a distributed architecture that simultaneously learns an RL policy and an intrinsic reward function.<n>We explore a range of algorithmic choices for reward modeling with varying complexity.<n>Our approach achieves state-of-the-art performance across a range of challenging tasks from the NetHack Learning Environment.
  arXiv  Detail & Related papers  (2024-10-30T13:52:43Z)
• Automatic AI Model Selection for Wireless Systems: Online Learning via Digital Twinning [50.332027356848094]
  AI-based applications are deployed at intelligent controllers to carry out functionalities like scheduling or power control. The mapping between context and AI model parameters is ideally done in a zero-shot fashion. This paper introduces a general methodology for the online optimization of AMS mappings.
  arXiv  Detail & Related papers  (2024-06-22T11:17:50Z)
• LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins [4.773175285216063]
  This paper presents a novel framework that applies large language models (LLMs) to automate the parametrization of simulation models in digital twins. The proposed approach enhances the usability of simulation model by infusing it with knowledges from LLM. The system has the potential to increase user-friendliness and reduce the cognitive load on human users.
  arXiv  Detail & Related papers  (2024-05-28T11:59:40Z)
• Towards Single-System Illusion in Software-Defined Vehicles -- Automated, AI-Powered Workflow [3.2821049498759094]
  We propose a novel model- and feature-based approach to development of vehicle software systems. One of the key points of the presented approach is the inclusion of modern generative AI, specifically Large Language Models (LLMs) The resulting pipeline is automated to a large extent, with feedback being generated at each step.
  arXiv  Detail & Related papers  (2024-03-21T15:07:57Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)

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.