# S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning

arXiv: https://arxiv.org/abs/2511.06727 · HTML: https://mlsanity.com/paper/2511.06727/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 19 of its 47 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- 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, 19 of 19)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [A Survey on Mixture of Experts in Large Language Models](https://mlsanity.com/paper/2407.06204/) (2024)
- [Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2410.02506/) (2024)
- [LLM Multi-Agent Systems: Challenges and Open Problems](https://mlsanity.com/paper/2402.03578/) (2024)
- [A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems](https://mlsanity.com/paper/2504.09037/) (2025)
- [LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models](https://mlsanity.com/paper/2404.01230/) (2024)
- [MasRouter: Learning to Route LLMs for Multi-Agent Systems](https://mlsanity.com/paper/2502.11133/) (2025)
- [A Survey of Large Language Model Agents for Question Answering](https://mlsanity.com/paper/2503.19213/) (2025)
- [SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents](https://mlsanity.com/paper/2411.03284/) (2024)
- [When One LLM Drools, Multi-LLM Collaboration Rules](https://mlsanity.com/paper/2502.04506/) (2025)
- [Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills](https://mlsanity.com/paper/2503.05641/) (2025)
- [Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems](https://mlsanity.com/paper/2502.04510/) (2025)
- [Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches](https://mlsanity.com/paper/2501.03151/) (2025)
- [AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning](https://mlsanity.com/paper/2411.16495/) (2024)

## Built on by (most cited first, 9 of 9)

- [Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection](https://mlsanity.com/paper/2601.09692/) (2026)
- [Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation](https://mlsanity.com/paper/2605.04922/) (2026)
- [Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval](https://mlsanity.com/paper/2604.15951/) (2026)
- [Workload-Aware Caching for Multi-Agent Systems](https://mlsanity.com/paper/2607.20495/) (2026)
- [BANDMAS: Causality-Inspired Semantic Packet Scheduling for Bandwidth-Efficient Multi-Agent Collaboration](https://mlsanity.com/paper/2608.00458/) (2026)
- [Structure for Reading, Prose for Writing: Asymmetric Structural Conditioning in Multi-Agent Document Authoring](https://mlsanity.com/paper/2608.20786/) (2026)
- [SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphs](https://mlsanity.com/paper/2609.10901/) (2026)
- [GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning](https://mlsanity.com/paper/2609.14066/) (2026)
- [JOVE: Joint Execution and Verification for Resource-Aware LLM Task Graphs](https://mlsanity.com/paper/2610.03296/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have achieved impressive performance in complex reasoning problems. Their effectiveness highly depends on the specific nature of the task, especially the required domain knowledge. Existing approaches, such as mixture-of-experts, typically operate at the task level; they are too coarse to effectively solve the heterogeneous problems involving multiple subjects. This work proposes a novel framework that performs fine-grained analysis at subject level equipped with a designated multi-agent collaboration strategy for addressing heterogeneous problem reasoning. Specifically, given an input query, we first employ a Graph Neural Network to identify the relevant subjects and infer their interdependencies to generate an textitSubject-based Directed Acyclic Graph (S-DAG), where nodes represent subjects and edges encode information flow. Then we profile the LLM models by assigning each model a subject-specific expertise score, and select the top-performing one for matching corresponding subject of the S-DAG. Such subject-model matching enables graph-structured multi-agent collaboration where information flows from the starting model to the ending model over S-DAG. We curate and release multi-subject subsets of standard benchmarks (MMLU-Pro, GPQA, MedMCQA) to better reflect complex, real-world reasoning tasks. Extensive experiments show that our approach significantly outperforms existing task-level model selection and multi-agent collaboration baselines in accuracy and efficiency. These results highlight the effectiveness of subject-aware reasoning and structured collaboration in addressing complex and multi-subject problems.