# AgentBalance: Backbone-then-Topology Design for Cost-Effective Multi-Agent Systems under Budget Constraints

arXiv: https://arxiv.org/abs/2512.11426 · HTML: https://mlsanity.com/paper/2512.11426/

## Key facts

- Cited by 4 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 57 references that are in the map.
- First posted on arXiv 12 Dec 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [RouterBench: A Benchmark for Multi-LLM Routing System](https://mlsanity.com/paper/2403.12031/) (2024)
- [Multi-agent Architecture Search via Agentic Supernet](https://mlsanity.com/paper/2502.04180/) (2025)
- [GraphRouter: A Graph-based Router for LLM Selections](https://mlsanity.com/paper/2410.03834/) (2024)
- [Lyfe Agents: Generative agents for low-cost real-time social interactions](https://mlsanity.com/paper/2310.02172/) (2023)
- [Offline Training of Language Model Agents with Functions as Learnable Weights](https://mlsanity.com/paper/2402.11359/) (2024)
- [Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2505.23352/) (2025)
- [Adaptive Graph Pruning for Multi-Agent Communication](https://mlsanity.com/paper/2506.02951/) (2025)
- [Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems](https://mlsanity.com/paper/2502.04510/) (2025)
- [Multi-Agent Systems for Robotic Autonomy with LLMs](https://mlsanity.com/paper/2505.05762/) (2025)
- [DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi](https://mlsanity.com/paper/2503.04768/) (2025)
- [MA4DIV: Multi-Agent Reinforcement Learning for Search Result Diversification](https://mlsanity.com/paper/2403.17421/) (2024)
- [LLM-Based Insight Extraction for Contact Center Analytics and Cost-Efficient Deployment](https://mlsanity.com/paper/2503.19090/) (2025)

## Built on by (most cited first, 4 of 4)

- [Agent-Omit: Adaptive Context Omission for Efficient LLM Agents](https://mlsanity.com/paper/2602.04284/) (2026)
- [LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning](https://mlsanity.com/paper/2605.14483/) (2026)
- [Multi-agent Framework for Time-Sensitive Complementary Collaboration in Minecraft](https://mlsanity.com/paper/2606.15684/) (2026)
- [EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications](https://mlsanity.com/paper/2610.16402/) (2026)

## Abstract (arXiv)

Large Language Model (LLM)-based multi-agent systems (MAS) are becoming indispensable building blocks for web-scale applications such as web search, social network analytics, and online customer support, where cost-effectiveness is increasingly the primary constraint for large-scale deployment. While recent work improves MAS cost-effectiveness by shaping inter-agent communication topologies and selecting agent backbones, it rarely models and optimizes under explicit token-cost and latency budgets that reflect deployment constraints. This often leads to topology-first designs and suboptimal cost-effectiveness when budgets are binding. We present AgentBalance, a framework for constructing cost-effective MAS under explicit token-cost and latency budgets via a backbone-then-topology design. AgentBalance first performs backbone-oriented agent generation, constructing agents with heterogeneous backbones through LLM pool construction, pool selection, and role-backbone matching. It then performs adaptive MAS topology generation, guiding inter-agent communication via agent representation learning, gating, and latency-aware topology synthesis. Experiments on benchmarks with 14 candidate LLM backbones show that AgentBalance achieves up to 10% and 22% performance gains under matched token-cost and latency budgets, respectively, and yields strong AUC on performance-versus-budget curves across benchmarks. AgentBalance also functions as a plug-in for existing MAS, improving performance under the same token-cost and latency constraints, and it generalizes well to unseen LLMs for practical, budget-aware deployment. Code: https://github.com/usail-hkust/AgentBalance