# RSIgen: Reciprocal Self-Improvement for Agentic Visual Generation

arXiv: https://arxiv.org/abs/2610.18688 · HTML: https://mlsanity.com/paper/2610.18688/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 28 of 28)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [Re-Imagen: Retrieval-Augmented Text-to-Image Generator](https://mlsanity.com/paper/2209.14491/) (2022)
- [T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT](https://mlsanity.com/paper/2505.00703/) (2025)
- [Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models](https://mlsanity.com/paper/2207.13038/) (2022)
- [Gen-Searcher: Reinforcing Agentic Search for Image Generation](https://mlsanity.com/paper/2603.28767/) (2026)
- [UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision](https://mlsanity.com/paper/2601.03193/) (2026)
- [Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation](https://mlsanity.com/paper/2602.01756/) (2026)
- [SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models](https://mlsanity.com/paper/2510.12784/) (2025)
- [GEMS: Agent-Native Multimodal Generation with Memory and Skills](https://mlsanity.com/paper/2603.28088/) (2026)
- [GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation](https://mlsanity.com/paper/2605.21605/) (2026)
- [HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation](https://mlsanity.com/paper/2502.12148/) (2025)
- [Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis](https://mlsanity.com/paper/2603.29620/) (2026)
- [UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation](https://mlsanity.com/paper/2603.23500/) (2026)
- [Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation](https://mlsanity.com/paper/2606.26907/) (2026)
- [Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs](https://mlsanity.com/paper/2507.16663/) (2025)
- [SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards](https://mlsanity.com/paper/2506.07963/) (2025)
- [Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation](https://mlsanity.com/paper/2607.05382/) (2026)
- [Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models](https://mlsanity.com/paper/2601.20305/) (2026)
- [Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards](https://mlsanity.com/paper/2606.27376/) (2026)
- [Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models](https://mlsanity.com/paper/2603.06043/) (2026)
- [UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts](https://mlsanity.com/paper/2510.17937/) (2025)
- [ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation](https://mlsanity.com/paper/2608.04436/) (2026)
- [Dreaming in Flow: Generative Grounding Feedback for Self-Evolving Unified Multimodal Models](https://mlsanity.com/paper/2609.08282/) (2026)

## Abstract (arXiv)

Agentic visual generation produces experience that can improve the native understanding (agent) and generation roles of a unified multimodal backbone, but task success alone does not determine which role should learn. Generator updates can also make the agent's action supervision stale. We introduce RSIgen, a task-centric reciprocal self-improvement framework linking learning allocation, supervision refresh, and recursive curriculum construction. Dynamic Responsibility Routing (DRR) uses matched interventions on evidence, inputs, and supported actions to select learning recipients and construct compatible training targets. After generator learning, RSIgen re-evaluates the relative utility of tested actions with branch inputs held fixed to refresh agent supervision; the retained roles then construct the next curriculum. Across BAGEL, Qwen-Image, and Wan-Image-7B, RSIgen improves AgentGen-Bench Full Overall9 by 3.2--3.3 points over a three-cycle SearchGen adaptation with action costs. Wan controls support allocation gains at matched role-level training exposure, refresh gains at a matched adaptation budget, and benefits from updated curriculum sources while recipients continue learning. In blind evaluation on 200 real-user requests, pooled tie-adjusted preference scores against the same baseline reach 70.0% for task completion and 64.9% for visual quality.