HieraMAS: Optimizing Intra-Node LLM Mixtures and Inter-Node Topology for Multi-Agent Systems

Tianjun Yao; Zhaoyi Li; Zhiqiang Shen

cs.MAFeb 23, 2026

HieraMAS: Optimizing Intra-Node LLM Mixtures and Inter-Node Topology for Multi-Agent Systems

Authors: Tianjun Yao, Zhaoyi Li, Zhiqiang Shen

Organizations: Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE.

Abstract

Multi-agent systems (MAS) built on large language models (LLMs) have shown strong performance across many tasks. Most existing approaches improve only one aspect at a time, such as the communication topology, role assignment, or LLM routing, while treating each agent as a single, indivisible unit. This misses the opportunity to use mixtures of LLMs within an agent to strengthen role-specific abilities. We propose HieraMAS, a hierarchical collaboration framework that combines intra-node LLM mixtures with an inter-node communication topology. HieraMAS introduces supernodes, where each functional role is implemented by multiple heterogeneous LLMs using a propose-synthesis structure. Optimizing HieraMAS creates unique credit-assignment challenges: final task performance depends heavily on the underlying LLMs' capabilities, which can lead reinforcement methods to incorrectly reward suboptimal configurations. To address this, we use a two-stage algorithm: (1) multi-level reward attribution, which provides fine-grained feedback at both the node level and the overall system level; (2) graph classification for topology selection, which treats choosing the communication structure as a holistic decision rather than optimizing edges one by one. Experiments on reasoning and coding benchmarks show that HieraMAS substantially outperforms existing methods while also delivering better cost-performance trade-offs.

Figures & tables

Figure 1: Illustration of two credit assignment challenges in joint optimization and our solutions. Challenge 1 : Final task rewards mask individual node errors—Node 2 produces incorrect output but receives high reward $R_{2}=0.92$ . HieraMAS addresses this via multi-level rewards that provide effective per-role attribution ( $R_{2}^{eff}=-0.23$ ). Challenge 2 : Per-edge optimization suffers from entangled attribution, where edges may be falsely reinforced or suppressed. HieraMAS reformulates topology selection as a holistic graph classification task, using a graph generator to produce candidates and a graph classifier to select the optimal topology.

Figure 2: The overall framework of HieraMAS . By optimizing a policy learner $\pi_{m}$ with multi-level rewards (Stage 1) and a graph classifier $f_{G}(\cdot)$ with contrastive rewards (Stage 2), HieraMAS learns to select optimal supernode configurations and communication topologies. During inference, the trained modules jointly determine the supernode configurations and graph topology, then execute the MAS to produce the final answer.

					HumanEval++		MATH		MMLU-Redux
Method	Multi	Topo	Role	Node	GPT-5-Mini	Qwen3-80B	GPT-5-Mini	Qwen3-80B	GPT-5-Mini	Qwen3-80B	Avg.
Base	✗	✗	✗	✗	89.06	84.14	77.78	74.44	92.00	82.40	83.14
CoT	✗	✗	✗	✗	87.50	85.94	92.22	90.00	93.60	89.60	89.81
Self-Consistency	✓	✗	✗	✗	89.06	87.50	93.33	91.11	94.40	83.20	89.77
Self-Consistency+CoT	✓	✗	✗	✗	90.62	85.94	94.44	92.22	93.60	92.80	91.60
LLM-Debate	✓	✗	✗	✗	87.50	87.50	94.44	94.44	92.80	92.00	91.45

Table 1: Main results on three benchmarks. We report accuracy (%) for each dataset. ✓ indicates the method uses the corresponding component: Multi = multi-agent, Topo = optimizing topology, Role = optimizing roles and LLMs in each role, Node = optimizing intra-node configuration. Best results are in bold , second best are underlined .

	MATH		MMLU-Redux
Variant	Acc	Cost	Acc	Cost
w/o Graph	93.33	1.57	92.00	1.36
w/o LLM Selection	97.78	2.56	94.40	3.92
Ours	96.67	1.52	95.20	1.29

Table 2: Ablation study on MATH and MMLU-Redux benchmarks. We evaluate the contribution of graph topology scoring and LLM selection. Acc (%) and Cost (USD) are reported.

Panel of Figure 3 — Figure 3: Analysis of learned topologies on MMLU-Redux. (a) Visualization of the top-3 most frequently selected graph structures with their density. (b) Pairwise Jaccard similarity between top-5 graphs, showing low structural overlap.

Figure 4: Dataset-level LLM selection preferences learned by HieraMAS . Normalized Logits indicate selection preference, with higher values indicating stronger preference.

Method	GPT-5-Mini	Qwen3-80B
SC+CoT	68.00	64.00
AFlow	72.00	68.00
GDesigner	72.00	68.00
MASRouter	56.00	68.00
Ours	68.00	72.00

Table 3: Generalization performance (%) on unseen MMLU categories. Best in bold , second best underlined .

Method	HumanEval++	MATH	MMLU
GDesigner	1.33	2.16	3.66
MASRouter	0.12	0.32	0.15
Ours	0.53	1.52	1.29

Table 4: Cost comparison ($). Lowest cost in bold .

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Symbol	Description	Symbol	Description
Search Space & Supernode Structure
$\mathbb{S}$	Search space $(\mathbb{M},\mathbb{R},\mathbb{G})$	$S_{i}$	Supernode $i$ with role $r_{i}$
$\mathbb{M}$	Pool of $N_{m}$ LLM backbones	$r_{i}$	Role for supernode $i$ , $r_{i}\in\mathbb{R}$
$\mathbb{R}$	Set of $N_{r}$ predefined agent roles	$W$	Number of proposers per supernode
$\mathbb{G}$	Space of graph topologies	$m_{i,j}^{(w)}$	LLM for $j$ -th proposer in supernode $i$
$\mathcal{G}$	Pool of $K$ candidate DAGs	$m_{i}^{(a)}$	LLM for synthesizer in supernode $i$

Appendix

Table 5: Summary of notation used in this paper.

Method	Acc (%)	Cost ($)
w/ 8 proposers	88.80	2.32
w/ 6 proposers	91.20	1.97
Ours (2 proposers)	95.20	1.29

Appendix

Table 6: Effect of the number of proposers per supernode on MMLU-Redux.

Method	Acc (%)
w/ $K=50$	93.60
w/ $K=500$	94.40
Ours ( $K=200$ )	95.60

Appendix

Table 7: Effect of graph pool size

K

on MMLU-Redux.

MMLU-Redux Case Studies
Case 1: Nutrition Question	Case 2: Communication Theory
Query: Which of the following appears to lower bad cholesterol? A. Vitamin D B. Niacin C. Thiamine D. Riboflavin	Query: According to “measurement,” what is the step that occurs between an individual gaining information and changing behavior? A. coorientation B. opinion change C. reaction formation D. semantic encoding

Appendix

Table 8: Case studies on MMLU-Redux. The typical configuration assigns GPT-5-Mini or GPT-5-Nano as proposers and GPT-5-Nano as the aggregator, favoring cost-efficient models for knowledge-intensive QA tasks.

HumanEval Case Studies
Case 1: Sum and Product	Case 2: Filter by Substring
Query: def sum_product(numbers: List[int]) -> Tuple[int, int]: """ For a given list of integers, return a tuple consisting of a sum and a product of all the integers in a list..."""	Query: def filter_by_substring(strings: List[str], substring: str) -> List[str]: """ Filter an input list of strings only for ones that contain given substring..."""

Appendix

Table 9: Case studies on HumanEval. The typical configuration assigns Qwen3-8B, Qwen3-80B, or LLaMA3.1-8B as proposers, leveraging diverse code-specialized models for programming tasks.

MATH Case Studies
Case 1: Geometry Reflection	Case 2: Cone Volume
Query: Triangle $ABC$ with vertices $A(-2,0)$ , $B(1,4)$ and $C(-3,2)$ is reflected over the $y$ -axis to form triangle $A^{\prime}B^{\prime}C^{\prime}$ . What is the length of a segment drawn from $C$ to $C^{\prime}$ ?	Query: The diameter of a cone is 30 decimeters. If the height is two times the radius, what is the volume of the cone in cubic decimeters?

Appendix

Table 10: Case studies on MATH. The typical configuration assigns Qwen3-8B combined with Qwen3-80B or DeepSeek-V3.2 as proposers, utilizing strong mathematical reasoning models.

Dataset	GDesigner	AFlow	MASRouter	Ours
MATH	$1.22	$18.62	$1.97	$2.03
HumanEval++	$1.95	$28.64	$0.54	$1.55
MMLU-Redux	$3.51	$13.94	$0.46	$1.85

Appendix

Table 11: Training cost comparison (in USD) across benchmarks.

Model	Profile Description
qwen3-8b	Fast and efficient 8B parameter model from Alibaba. Very fast inference, low latency, cost-effective. Good for basic text generation and simple Q&A. Very low cost.
qwen3-80b	Powerful 80B mixture-of-experts model from Alibaba. Strong reasoning, excellent at complex tasks, good at math and coding. Good for complex reasoning and mathematical problem-solving. Medium-high cost.
deepseek-r1-14b	Math-focused 14B model optimized for reasoning. Excellent mathematical reasoning and step-by-step problem solving. Good for math problems and logical reasoning. Low-medium cost.
llama-8b	General-purpose 8B model from Meta. Well-balanced capabilities with good instruction following. Good for general tasks, conversation, and basic reasoning. Very low cost.
deepseek-v3	State-of-the-art reasoning model with excellent performance. Top-tier reasoning, excellent at complex problems, strong coding ability. Good for complex reasoning and advanced math. Medium cost.
gemma-3-27b	Balanced 27B model from Google. Good balance of speed and capability with strong instruction following. Good for medium complexity tasks. Medium cost.

Appendix

Table 12: LLM profiles used for embedding-based model selection. Each profile describes model strengths, cost tier, and recommended use cases.

Role	Profile Description
Mathematical Reasoning Roles (MATH benchmark)
Mathematical Analyst	Specialized in breaking down complex math problems. Identifies mathematical structure, defines variables, and sets up equations. Best for initial problem understanding and mathematical modeling.
Math Solver	Specialized in executing mathematical computations. Solves equations, performs calculations, and verifies numerical results. Best for carrying out calculations and deriving numerical answers.
Inspector	Specialized in reviewing and validating solutions. Checks solution correctness, identifies errors, and verifies final answers. Best for final verification and error catching.
Programming Roles (HumanEval benchmark)
Project Manager	Specialized in design patterns and code structure. Coordinates solution strategy and organizes workflow. Best for complex problems requiring structured multi-step approaches.

Appendix

Table 13: Role profiles used for embedding-based role assignment. Roles are categorized by their primary application domain.

Communication Topology Optimization

See all 11 papers

Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning
Apr 1, 2026Eric Hanchen Jiang, Levina Li, Rui Sun +9Multi-Agent Communication Topology Multi-Agent Reasoning
University of California Los Angeles · University of Washington · Northwestern University
Competence-Aware Orchestration for LLM-Based Multi-Agent Systems
Oct 9, 2026Songmiao Wang, Yuchen Wang, Chenglin Yu +2LLM Agent Orchestration Multi-Agent LLM Systems
The Hong Kong Polytechnic University
HELENA:Hierarchical Sparse Coordination over a Union of Complementary Topologies for MAS
Aug 5, 2026Zhifang Mao, Linyao Zheng, Xuhang Shi +1Multi-Agent LLM Systems Multi-Agent Coordination
1XiaoLab · 2Xi’an Jiaotong University · 3Beijing University of Posts and Telecommunications

Apr 1, 2026J/K move · Enter open · S save

Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning

Eric Hanchen Jiang, Levina Li, Rui Sun, Xiao Liang+8

University of California Los Angeles · University of Washington · Northwestern University

Multi-Agent Communication Topology Multi-Agent Reasoning Multi-Agent Communication RL for LLM Agents Cooperative MARL

Open paper AskPDF arXiv

Large Language Models (LLMs) have shown remarkable performance in completing various tasks. However, solving complex problems often requires the coordination of multiple agents, raising a fundamental question: how to effectively select and interconnect these agents. In this paper, we propose Agent Q-Mix, a reinforcement learning framework that reformulates topology selection as a cooperative Multi-Agent Reinforcement Learning (MARL) problem. Our method learns decentralized communication decisions using QMIX value factorization, where each agent selects from a set of communication actions that jointly induce a round-wise communication graph. At its core, Agent Q-Mix combines a topology-aware GNN encoder, GRU memory, and per-agent Q-heads under a Centralized Training with Decentralized Execution (CTDE) paradigm. The framework optimizes a reward function that balances task accuracy with token cost. Across seven core benchmarks in coding, reasoning, and mathematics, Agent Q-Mix achieves the highest average accuracy compared to existing methods while demonstrating superior token efficiency and robustness against agent failure. Notably, on the challenging Humanity's Last Exam (HLE) using Gemini-3.1-Flash-Lite as a backbone, Agent Q-Mix achieves 20.8% accuracy, outperforming Microsoft Agent Framework (19.2%) and LangGraph (19.2%), followed by AutoGen and Lobster by OpenClaw. These results underscore the effectiveness of learned, decentralized topology optimization in pushing the boundaries of multi-agent reasoning.

Abstract

Communication Topology Optimization

Explore similar work

Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning

Competence-Aware Orchestration for LLM-Based Multi-Agent Systems

HELENA:Hierarchical Sparse Coordination over a Union of Complementary Topologies for MAS