mlsanityData to 14 Oct 2026

BAMAS: Structuring Budget-Aware Multi-Agent Systems

arXiv 2511.21572 ↗First posted 26 Nov 2025cs.MA cs.AIcited by 6

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Large language model (LLM)-based multi-agent systems have emerged as a powerful paradigm for enabling autonomous agents to solve complex tasks. As these systems scale in complexity, cost becomes an important consideration for practical deployment. However, existing work rarely addresses how to structure multi-agent systems under explicit budget constraints. In this paper, we propose BAMAS, a novel approach for building multi-agent systems with budget awareness. BAMAS first selects an optimal set of LLMs by formulating and solving an Integer Linear Programming problem that balances performance and cost. It then determines how these LLMs should collaborate by leveraging a reinforcement learning-based method to select the interaction topology. Finally, the system is instantiated and executed based on the selected agents and their collaboration topology. We evaluate BAMAS on three representative tasks and compare it with state-of-the-art agent construction methods. Results show that BAMAS achieves comparable performance while reducing cost by up to 86%.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 23 of its 34 references that are in the map. First posted on arXiv 26 Nov 2025.

Builds on

23 of 34 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application23 Dec
  2. 2024A Unified Approach to Routing and Cascading for LLMs14 Oct

Other references · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  7. 2021Program Synthesis with Large Language Modelscited by 3,637
  8. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  9. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  10. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  11. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  12. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,184
9 more
  1. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  2. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  3. 2016Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learningcited by 286
  4. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 178
  5. 2019Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Samplingcited by 119
  6. 2024Large Language Model Inference Acceleration: A Comprehensive Hardware Perspectivecited by 38
  7. 2025Steering LLM Thinking with Budget Guidancecited by 33
  8. 2025Cost-Saving LLM Cascades with Early Abstentioncited by 14
  9. 2024Efficient Contextual LLM Cascades through Budget-Constrained Policy Learningcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2026ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestrationcited by 2
  2. 2025FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaborationcited by 1
  3. 2026Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraftcited by 1
  4. 2026Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utilitycited by 0
  5. 2026Competing at Every Price Point with Agentic Evolution over a Menu of LLMscited by 0
  6. 2026Truthful and Expected-Payment-Optimal Model Routing in Graph-Based Agentic Workflowscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning
  2. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges
  3. 2026SC-MAS: Constructing Cost-Efficient Multi-Agent Systems with Edge-Level Heterogeneous Collaboration
  4. 2025AgentBalance: Backbone-then-Topology Design for Cost-Effective Multi-Agent Systems under Budget Constraints
  5. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  6. 2025Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy
  7. 2025Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordination
  8. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects