Beyond Local Code Optimization: Multi-Agent Reasoning for Software System Optimization

• URL: http://arxiv.org/abs/2603.14703v1
• Date: Mon, 16 Mar 2026 01:21:50 GMT
• Title: Beyond Local Code Optimization: Multi-Agent Reasoning for Software System Optimization
• Abstract summary: Large language models and AI agents have recently shown promise in automating software performance optimization.<n>Existing approaches predominantly rely on local, syntax-driven code.<n>This paper introduces a multi-agent framework that integrates control-flow and data-flow representations with architectural and cross-component dependency signals.
• Score: 6.321658281654116
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models and AI agents have recently shown promise in automating software performance optimization, but existing approaches predominantly rely on local, syntax-driven code transformations. This limits their ability to reason about program behavior and capture whole system performance interactions. As modern software increasingly comprises interacting components - such as microservices, databases, and shared infrastructure - effective code optimization requires reasoning about program structure and system architecture beyond individual functions or files. This paper explores the feasibility of whole system optimization for microservices. We introduce a multi-agent framework that integrates control-flow and data-flow representations with architectural and cross-component dependency signals to support system-level performance reasoning. The proposed system is decomposed into coordinated agent roles - summarization, analysis, optimization, and verification - that collaboratively identify cross-cutting bottlenecks and construct multi-step optimization strategies spanning the software stack. We present a proof-of-concept on a microservice-based system that illustrates the effectiveness of our proposed framework, achieving a 36.58% improvement in throughput and a 27.81% reduction in average response time.

Related papers

• The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows [72.9051182568928]
  We present ReASearch, a unified framework for reasoning-driven optimization.<n>With a shared agent loop and domain-specific tools, ReASearch instantiates the exact same scaffold to optimize prompts, programs, and ML.<n>We observe that complex search behaviors emerge naturally from the agent's reasoning process.
  arXiv  Detail & Related papers  (2026-08-07T02:15:39Z)
• Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization [18.683909290649876]
  "Agent Engineering" is the process of designing and optimizing multi-agent systems.<n>TPGO is a framework that enables a multi-agent system to learn to evolve.<n>The core of our framework is Group Relative Agent Optimization (GRAO), a novel meta-learning strategy.
  arXiv  Detail & Related papers  (2026-04-22T16:00:46Z)
• VeriAgent: A Tool-Integrated Multi-Agent System with Evolving Memory for PPA-Aware RTL Code Generation [52.43796056267479]
  We propose a PPA-aware, tool-integrated multi-agent framework for high-quality verilog code generation.<n>Our framework explicitly incorporates EDA tools into a closed-loop workflow composed of a textitProgrammer Agent, a textitCorrectness Agent, and a textitPPA Agent<n>To support continuous improvement without model retraining, we introduce an textitEvolved Memory Mechanism that externalizes optimization experience into structured memory nodes.
  arXiv  Detail & Related papers  (2026-03-18T11:25:40Z)
• CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization [5.592208774984063]
  CODMAS is a framework that combines structured dialectic reasoning with domain-aware code generation and deterministic evaluation.<n>We introduce RTLOPT, a benchmark of 120 Verilog triples (unoptimized, optimized, testbench) for pipelining and clock-gating transformations.
  arXiv  Detail & Related papers  (2026-03-17T23:10:07Z)
• LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering [90.84806758077536]
  We introduce textbfLoCoBench-Agent, a comprehensive evaluation framework specifically designed to assess large language models (LLMs) agents in realistic, long-context software engineering.<n>Our framework extends LoCoBench's 8,000 scenarios into interactive agent environments, enabling systematic evaluation of multi-turn conversations.<n>Our framework provides agents with 8 specialized tools (file operations, search, code analysis) and evaluates them across context lengths ranging from 10K to 1M tokens.
  arXiv  Detail & Related papers  (2025-11-17T23:57:24Z)
• KForge: Program Synthesis for Diverse AI Hardware Accelerators [5.967639357025406]
  We present KForge, a platform-agnostic framework built on two collaborative LLM-based agents.<n>A generation agent produces and iteratively refines programs through compilation and correctness feedback, and a performance analysis agent interprets profiling data to guide optimization.<n>This agent-based architecture requires only a single-shot example to target new platforms.
  arXiv  Detail & Related papers  (2025-11-17T11:46:43Z)
• AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework [42.57224438231615]
  This paper introduces textbfAwareCompiler, an agentic framework for compiler optimization.<n>Three key innovations: structured knowledge integration and dataset construction, knowledge-driven adaptive pass generation, and data-driven hybrid training pipeline.<n> Experimental results on standard benchmarks demonstrate that AwareCompiler significantly outperforms existing baselines in both performance and efficiency.
  arXiv  Detail & Related papers  (2025-10-13T02:02:36Z)
• Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution [48.7788770680643]
  Flash-Searcher is a novel parallel agent reasoning framework.<n>It decomposes complex tasks into subtasks with explicit dependencies, enabling concurrent execution of independent reasoning paths.<n>It achieves 67.7% accuracy on BrowseComp and 83% on xbench-DeepSearch, while reducing agent execution steps by up to 35% compared to current frameworks.
  arXiv  Detail & Related papers  (2025-09-29T17:39:30Z)
• Towards Agentic OS: An LLM Agent Framework for Linux Schedulers [3.8068085728995307]
  We introduce SchedCP, the first framework that enables fully autonomous Large Language Model (LLM) agents to safely and efficiently optimize Linux schedulers without human involvement.<n>Our evaluation shows that SchedCP achieves up to an 1.79x performance improvement, and a 13x cost reduction compared to naive agentic approaches.
  arXiv  Detail & Related papers  (2025-09-01T08:38:49Z)
• Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards [98.0983122471875]
  We propose Optimas, a unified framework for effective optimization of compound systems.<n>In each iteration, Optimas efficiently adapts the Local Reward Function (LRF) to maintain this property while simultaneously maximizing each component's local reward.<n>We present extensive evaluations across five real-world compound systems to demonstrate that Optimas outperforms strong baselines by an average improvement of 11.92%.
  arXiv  Detail & Related papers  (2025-07-03T07:12:48Z)
• SysLLMatic: Large Language Models are Software System Optimizers [5.342249053033864]
  We present SysLLMatic, a system that integrates LLMs with performance diagnostics feedback and a curated catalog of 43 optimization patterns.<n>We evaluate it on three benchmark suites: HumanEval_ CPP (competitive programming in C++), SciMark2 (scientific kernels in Java), and DaCapoBench (large-scale software systems in Java)<n>Results show that SysLLMatic can improve software system performance, including latency, throughput energy efficiency, memory usage, and CPU utilization.
  arXiv  Detail & Related papers  (2025-06-02T01:57:21Z)
• Towards more Contextual Agents: An extractor-Generator Optimization Framework [0.0]
  Large Language Model (LLM)-based agents have demonstrated remarkable success in solving complex tasks across a wide range of general-purpose applications.<n>However, their performance often degrades in context-specific scenarios, such as specialized industries or research domains.<n>To address this challenge, our work introduces a systematic approach to enhance the contextual adaptability of LLM-based agents.
  arXiv  Detail & Related papers  (2025-02-18T15:07:06Z)
• Federated Multi-Level Optimization over Decentralized Networks [55.776919718214224]
  We study the problem of distributed multi-level optimization over a network, where agents can only communicate with their immediate neighbors. We propose a novel gossip-based distributed multi-level optimization algorithm that enables networked agents to solve optimization problems at different levels in a single timescale. Our algorithm achieves optimal sample complexity, scaling linearly with the network size, and demonstrates state-of-the-art performance on various applications.
  arXiv  Detail & Related papers  (2023-10-10T00:21:10Z)

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.