Towards Scalable Customization and Deployment of Multi-Agent Systems for Enterprise Applications
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
Large language model (LLM)-based multi-agent systems demonstrate strong performance on complex reasoning and task execution, enabling broad enterprise applications. However, production deployment remains challenging due to domain-specific customization requirements and high latency and inference costs in agentic workflows. We propose a unified framework for customization and efficient deployment of multi-agent systems in real-world settings. The first stage, Agentic Model Customization, combines continual pretraining, supervised fine-tuning, and preference optimization to adapt a compact model to specialized domains while retaining strong agentic capabilities. The second stage, Inference Optimization, integrates speculative decoding and FP8 quantization with targeted calibration to enable cost-efficient serving with minimal quality loss. Across enterprise workloads, our framework enables rapid domain adaptation and achieves a 4.48x speedup in throughput while maintaining performance and improving robustness on long-tail scenarios.
Key facts. No citing papers in the map yet (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 18 of its 26 references that are in the map. First posted on arXiv 16 Jun 2026.
Builds on
18 of 26 references.
References · 18
- 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
- 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
- 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
- 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 1,006
- 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 812
- 2024EAGLE: Speculative Sampling Requires Rethinking Feature Uncertaintycited by 578
- 2024EAGLE-2: Faster Inference of Language Models with Dynamic Draft Treescited by 370
- 2025EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Testcited by 331
- 2022FP8 Quantization: The Power of the Exponentcited by 88
- 2024Scaling FP8 training to trillion-token LLMscited by 65
- 2024Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agentscited by 56
- 2023Efficient Post-training Quantization with FP8 Formatscited by 29
6 more
- 2023Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learningcited by 27
- 2024Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skillscited by 26
- 2025Alignment for Efficient Tool Calling of Large Language Modelscited by 17
- 2025T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planningcited by 14
- 2024Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectivescited by 13
- 2025Optimizing Reasoning Efficiency through Prompt Difficulty Predictioncited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback
- 2025Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
- 2026AgentFactory: Towards Automated Agentic System Design and Optimization
- 2025Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows
- 2026LLM-Enabled Multi-Agent Systems: Empirical Evaluation and Insights into Emerging Design Patterns & Paradigms
- 2024A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops
- 2025Agent Fine-tuning through Distillation for Domain-specific LLMs in Microdomains
- 2024Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions