# HiveMind: Contribution-Guided Online Prompt Optimization of LLM Multi-Agent Systems

arXiv: https://arxiv.org/abs/2512.06432 · HTML: https://mlsanity.com/paper/2512.06432/

## Key facts

- Cited by 7 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 9 of its 24 references that are in the map.
- First posted on arXiv 6 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, 9 of 9)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Value-Decomposition Networks For Cooperative Multi-Agent Learning](https://mlsanity.com/paper/1706.05296/) (2017)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [A Survey of Automatic Prompt Engineering: An Optimization Perspective](https://mlsanity.com/paper/2502.11560/) (2025)
- [Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents](https://mlsanity.com/paper/2506.07388/) (2025)

## Built on by (most cited first, 7 of 7)

- [EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering](https://mlsanity.com/paper/2604.05149/) (2026)
- [Agentic Trading: When LLM Agents Meet Financial Markets](https://mlsanity.com/paper/2605.19337/) (2026)
- [MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?](https://mlsanity.com/paper/2606.23664/) (2026)
- [DAO-Agent: Zero Knowledge-Verified Incentives for Decentralized Multi-Agent Coordination](https://mlsanity.com/paper/2512.20973/) (2025)
- [CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution](https://mlsanity.com/paper/2605.13295/) (2026)
- [Code Broker: A Multi-Agent System for Automated Code Quality Assessment](https://mlsanity.com/paper/2604.23088/) (2026)
- [Agents that Matter: Optimizing Multi-Agent LLMs via Removal-Based Attribution](https://mlsanity.com/paper/2605.27621/) (2026)

## Abstract (arXiv)

Recent advances in LLM-based multi-agent systems have demonstrated remarkable capabilities in complex decision-making scenarios such as financial trading and software engineering. However, evaluating each individual agent's effectiveness and online optimization of underperforming agents remain open challenges. To address these issues, we present HiveMind, a self-adaptive framework designed to optimize LLM multi-agent collaboration through contribution analysis. At its core, HiveMind introduces Contribution-Guided Online Prompt Optimization (CG-OPO), which autonomously refines agent prompts based on their quantified contributions. We first propose the Shapley value as a grounded metric to quantify each agent's contribution, thereby identifying underperforming agents in a principled manner for automated prompt refinement. To overcome the computational complexity of the classical Shapley value, we present DAG-Shapley, a novel and efficient attribution algorithm that leverages the inherent Directed Acyclic Graph structure of the agent workflow to axiomatically prune non-viable coalitions. By hierarchically reusing intermediate outputs of agents in the DAG, our method further reduces redundant computations, and achieving substantial cost savings without compromising the theoretical guarantees of Shapley values. Evaluated in a multi-agent stock-trading scenario, HiveMind achieves superior performance compared to static baselines. Notably, DAG-Shapley reduces LLM calls by over 80% while maintaining attribution accuracy comparable to full Shapley values, establishing a new standard for efficient credit assignment and enabling scalable, real-world optimization of multi-agent collaboration.