Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning

• URL: http://arxiv.org/abs/2511.02755v1
• Date: Tue, 04 Nov 2025 17:35:17 GMT
• Title: Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning
• Authors: Bowen Jin, TJ Collins, Donghan Yu, Mert Cemri, Shenao Zhang, Mengyu Li, Jay Tang, Tian Qin, Zhiyang Xu, Jiarui Lu, Guoli Yin, Jiawei Han, Zirui Wang,
• Abstract summary: Large language models (LLMs) exhibit complementary strengths across domains and come with varying inference costs.<n>Existing approaches rely on decentralized frameworks, which invoke multiple LLMs for every input and thus lead to substantial and uncontrolled inference costs.<n>We introduce a centralized multi-LLM framework, where a controller LLM selectively coordinates a pool of expert models in a cost-efficient and cost-controllable manner.
• Score: 53.57360296655208
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) exhibit complementary strengths across domains and come with varying inference costs, motivating the design of multi-agent LLM systems where specialized models collaborate efficiently. Existing approaches predominantly rely on decentralized frameworks, which invoke multiple LLMs for every input and thus lead to substantial and uncontrolled inference costs. In this work, we introduce a centralized multi-LLM framework, where a controller LLM selectively coordinates a pool of expert models in a cost-efficient and cost-controllable manner. We formulate this coordination problem as reinforcement learning with dual objectives: maximizing task performance while minimizing the overall inference cost. In addition, we expect the multi-agent system to have adapted behavior with different budget conditions during inference. To this end, we propose CoRL, a reinforcement learning framework that optimizes the performance cost trade-off in a controllable multi-budget setting. Experiments on four diverse benchmarks demonstrate that CoRL enables a single system to surpass the best expert LLM under high-budget settings, while maintaining strong performance in more economical low-budget modes, highlighting the effectiveness of centralized coordination for scalable and cost-efficient multi-agent LLM systems.

Related papers

• BAMAS: Structuring Budget-Aware Multi-Agent Systems [18.99441110805831]
  Large language model (LLM)-based multi-agent systems have emerged as a powerful paradigm for enabling autonomous agents to solve complex tasks.<n>We propose BAMAS, a novel approach for building multi-agent systems with budget awareness.<n>Results show that BAMAS achieves comparable performance while reducing cost by up to 86%.
  arXiv  Detail & Related papers  (2025-11-26T16:48:18Z)
• MALBO: Optimizing LLM-Based Multi-Agent Teams via Multi-Objective Bayesian Optimization [0.0]
  This thesis introduces MALBO, a systematic framework designed to automate the efficient composition of multi-agent AI teams.<n>We formalize the assignment challenge as a multi-objective optimization problem, aiming to identify the front of configurations between task accuracy and inference cost.<n>Our results demonstrate that the Bayesian optimization phase, compared to an initial random search, maintained a comparable average performance while reducing the average configuration cost by over 45%.
  arXiv  Detail & Related papers  (2025-11-14T18:01:08Z)
• Heterogeneous Group-Based Reinforcement Learning for LLM-based Multi-Agent Systems [25.882461853973897]
  We propose Multi-Agent Heterogeneous Group Policy Optimization (MHGPO), which guides policy updates by estimating relative reward advantages.<n>MHGPO eliminates the need for Critic networks, enhancing stability and reducing computational overhead.<n>We also introduce three group rollout sampling strategies that trade off between efficiency and effectiveness.
  arXiv  Detail & Related papers  (2025-06-03T10:17:19Z)
• RLAE: Reinforcement Learning-Assisted Ensemble for LLMs [21.77261258691006]
  Large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks.<n>We propose Reinforcement Learning-Assisted Ensemble for LLMs, a novel framework that reformulates ensemble through the lens of a Markov Decision Process (MDP)<n>Our approach introduces a RL agent that dynamically adjusts ensemble weights by considering both input context and intermediate generation states.
  arXiv  Detail & Related papers  (2025-05-31T07:38:41Z)
• LightRouter: Towards Efficient LLM Collaboration with Minimal Overhead [19.573553157421774]
  Light is a novel framework designed to systematically select and integrate a small subset of LLMs from a larger pool.<n>Experiments demonstrate that Light matches or outperforms widely-used ensemble baselines, achieving up to a 25% improvement in accuracy.<n>This work introduces a practical approach for efficient LLM selection and provides valuable insights into optimal strategies for model combination.
  arXiv  Detail & Related papers  (2025-05-22T04:46:04Z)
• Collab: Controlled Decoding using Mixture of Agents for LLM Alignment [90.6117569025754]
  Reinforcement learning from human feedback has emerged as an effective technique to align Large Language models.<n>Controlled Decoding provides a mechanism for aligning a model at inference time without retraining.<n>We propose a mixture of agent-based decoding strategies leveraging the existing off-the-shelf aligned LLM policies.
  arXiv  Detail & Related papers  (2025-03-27T17:34:25Z)
• Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agents [31.341487297459995]
  This paper introduces RL-Focal, a two-stage RL agent framework that routes and ensembles LLMs.<n>By focal diversity, we enhance performance across tasks by effectively promoting reward-aware and policy-adaptive ensemble selection and inference fusion.
  arXiv  Detail & Related papers  (2025-02-06T20:44:26Z)
• MALT: Improving Reasoning with Multi-Agent LLM Training [67.76186488361685]
  MALT (Multi-Agent LLM Training) is a novel post-training strategy that divides the reasoning process into generation, verification, and refinement steps.<n>On MATH, GSM8K, and CSQA, MALT surpasses the same baseline LLM with a relative improvement of 15.66%, 7.42%, and 9.40% respectively.
  arXiv  Detail & Related papers  (2024-12-02T19:30:36Z)
• MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming [10.461509044478278]
  MaCTG (MultiAgent Collaborative Thought Graph) is a novel multi-agent framework that employs a dynamic graph structure.<n>It autonomously assigns agent roles based on programming requirements, dynamically refines task distribution, and systematically verifies and integrates project-level code.<n>MaCTG significantly reduced operational costs by 89.09% compared to existing multi-agent frameworks.
  arXiv  Detail & Related papers  (2024-10-25T01:52:15Z)
• A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs [74.35290684163718]
  A primary challenge in large language model (LLM) development is their onerous pre-training cost. This paper explores a promising paradigm to improve LLM pre-training efficiency and quality by leveraging a small language model (SLM)
  arXiv  Detail & Related papers  (2024-10-24T14:31:52Z)
• CoMMIT: Coordinated Multimodal Instruction Tuning [90.1532838391285]
  Multimodal large language models (MLLMs) generally involve cooperative learning between a backbone LLM and a feature encoder of non-text input modalities.<n>In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives.<n>We propose a Multimodal Balance Coefficient that enables quantitative measurement of the balance of learning.
  arXiv  Detail & Related papers  (2024-07-29T23:18:55Z)
• Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration [83.4031923134958]
  Corex is a suite of novel general-purpose strategies that transform Large Language Models into autonomous agents. Inspired by human behaviors, Corex is constituted by diverse collaboration paradigms including Debate, Review, and Retrieve modes. We demonstrate that orchestrating multiple LLMs to work in concert yields substantially better performance compared to existing methods.
  arXiv  Detail & Related papers  (2023-09-30T07:11:39Z)
• Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
  We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
  arXiv  Detail & Related papers  (2021-07-08T18:01:02Z)

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.