Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards

• URL: http://arxiv.org/abs/2507.03041v2
• Date: Wed, 09 Jul 2025 18:47:51 GMT
• Title: Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards
• Authors: Shirley Wu, Parth Sarthi, Shiyu Zhao, Aaron Lee, Herumb Shandilya, Adrian Mladenic Grobelnik, Nurendra Choudhary, Eddie Huang, Karthik Subbian, Linjun Zhang, Diyi Yang, James Zou, Jure Leskovec,
• Abstract summary: 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%.
• Score: 95.19837878559456
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Compound AI systems integrating multiple components, such as Large Language Models, specialized tools, and traditional machine learning models, are increasingly deployed to solve complex real-world tasks. However, optimizing compound systems remains challenging due to their non-differentiable structures and diverse configuration types across components, including prompts, hyperparameters, and model parameters. To address this challenge, we propose Optimas, a unified framework for effective optimization of compound systems. The core idea of Optimas is to maintain one Local Reward Function (LRF) per component, each satisfying a local-global alignment property, i.e., each component's local reward correlates with the global system performance. In each iteration, Optimas efficiently adapts the LRFs to maintain this property while simultaneously maximizing each component's local reward. This approach enables independent updates of heterogeneous configurations using the designated optimization method, while ensuring that local improvements consistently lead to performance gains. We present extensive evaluations across five real-world compound systems to demonstrate that Optimas outperforms strong baselines by an average improvement of 11.92%, offering a general and effective approach for improving compound systems. Our website is at https://optimas.stanford.edu.

Related papers

• LLM as a Complementary Optimizer to Gradient Descent: A Case Study in Prompt Tuning [69.95292905263393]
  We show that gradient-based and high-level LLMs can effectively collaborate a combined optimization framework.<n>In this paper, we show that these complementary to each other and can effectively collaborate a combined optimization framework.
  arXiv  Detail & Related papers  (2024-05-30T06:24:14Z)
• Localized Zeroth-Order Prompt Optimization [54.964765668688806]
  We propose a novel algorithm, namely localized zeroth-order prompt optimization (ZOPO) ZOPO incorporates a Neural Tangent Kernel-based derived Gaussian process into standard zeroth-order optimization for an efficient search of well-performing local optima in prompt optimization. Remarkably, ZOPO outperforms existing baselines in terms of both the optimization performance and the query efficiency.
  arXiv  Detail & Related papers  (2024-03-05T14:18:15Z)
• CURE: Simulation-Augmented Auto-Tuning in Robotics [15.943773140929856]
  This paper proposes CURE -- a method that identifies causally relevant configuration options.<n>CURE abstracts the causal relationships between various configuration options and robot performance objectives.<n>We demonstrate the effectiveness and transferability of CURE by conducting experiments in both physical robots and simulation.
  arXiv  Detail & Related papers  (2024-02-08T04:27:14Z)
• Analyzing and Enhancing the Backward-Pass Convergence of Unrolled Optimization [50.38518771642365]
  The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks. A central challenge in this setting is backpropagation through the solution of an optimization problem, which often lacks a closed form. This paper provides theoretical insights into the backward pass of unrolled optimization, showing that it is equivalent to the solution of a linear system by a particular iterative method. A system called Folded Optimization is proposed to construct more efficient backpropagation rules from unrolled solver implementations.
  arXiv  Detail & Related papers  (2023-12-28T23:15:18Z)
• 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)
• A Bayesian Optimization Framework for Finding Local Optima in Expensive Multi-Modal Functions [18.570591025615453]
  This paper develops a multimodal BO framework to find a set of local/global solutions for expensive-to-evaluate multimodal objective functions. We analytically derive the joint distribution of the objective function and its first-order derivatives. We introduce variants of the well-known BO acquisition functions to the multimodal setting and demonstrate the performance of the proposed framework.
  arXiv  Detail & Related papers  (2022-10-13T00:10:13Z)
• Accelerated Federated Learning with Decoupled Adaptive Optimization [53.230515878096426]
  federated learning (FL) framework enables clients to collaboratively learn a shared model while keeping privacy of training data on clients. Recently, many iterations efforts have been made to generalize centralized adaptive optimization methods, such as SGDM, Adam, AdaGrad, etc., to federated settings. This work aims to develop novel adaptive optimization methods for FL from the perspective of dynamics of ordinary differential equations (ODEs)
  arXiv  Detail & Related papers  (2022-07-14T22:46:43Z)
• Hierarchical Segment-based Optimization for SLAM [6.590648135605555]
  This paper presents a hierarchical segment-based optimization method for Simultaneous Localization and Mapping (SLAM) system. First we propose a reliable trajectory segmentation method that can be used to increase efficiency in the back-end optimization. Then we propose a buffer mechanism for the first time to improve the robustness of the segmentation.
  arXiv  Detail & Related papers  (2021-11-07T14:57:26Z)
• Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks [17.370056935194786]
  We propose Batch Multi-fidelity Bayesian Optimization with Deep Auto-Regressive Networks (BMBO-DARN) We use a set of Bayesian neural networks to construct a fully auto-regressive model, which is expressive enough to capture strong yet complex relationships across all fidelities. We develop a simple yet efficient batch querying method, without any search over fidelities.
  arXiv  Detail & Related papers  (2021-06-18T02:55:48Z)

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.