# Collaborative Text-to-Image Generation via Multi-Agent Reinforcement Learning and Semantic Fusion

arXiv: https://arxiv.org/abs/2510.10633 · HTML: https://mlsanity.com/paper/2510.10633/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 33 references that are in the map.
- First posted on arXiv 12 Oct 2025.

## Builds on (most cited first, 3 of 3)

- [Image Fusion Transformer](https://mlsanity.com/paper/2107.09011/) (2021)
- [Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation](https://mlsanity.com/paper/2403.16422/) (2024)
- [MATCNN: Infrared and Visible Image Fusion Method Based on Multi-scale CNN with Attention Transformer](https://mlsanity.com/paper/2502.01959/) (2025)

## Built on by (most cited first, 1 of 1)

- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)

## Abstract (arXiv)

Multimodal text-to-image generation remains constrained by the difficulty of maintaining semantic alignment and professional-level detail across diverse visual domains. We propose a multi-agent reinforcement learning framework that coordinates domain-specialized agents (e.g., focused on architecture, portraiture, and landscape imagery) within two coupled subsystems: a text enhancement module and an image generation module, each augmented with multimodal integration components. Agents are trained using Proximal Policy Optimization (PPO) under a composite reward function that balances semantic similarity, linguistic visual quality, and content diversity. Cross-modal alignment is enforced through contrastive learning, bidirectional attention, and iterative feedback between text and image. Across six experimental settings, our system significantly enriches generated content (word count increased by 1614%) while reducing ROUGE-1 scores by 69.7%. Among fusion methods, Transformer-based strategies achieve the highest composite score (0.521), despite occasional stability issues. Multimodal ensembles yield moderate consistency (ranging from 0.444 to 0.481), reflecting the persistent challenges of cross-modal semantic grounding. These findings underscore the promise of collaborative, specialization-driven architectures for advancing reliable multimodal generative systems.