# DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editing

arXiv: https://arxiv.org/abs/2608.20161 · HTML: https://mlsanity.com/paper/2608.20161/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 0 of its 42 references that are in the map.
- First posted on arXiv 20 Aug 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/)
- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

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

- [DuplexBridge: Coordinating Understanding and Generation for Unified Image Editing](https://mlsanity.com/paper/2610.18819/) (2026)

## Abstract (arXiv)

Instruction-based image editing uses a planner-renderer pipeline: a vision-language model (VLM) first converts the instruction into an edit plan, and a diffusion model then executes that plan. Training such systems with only final-image rewards is inefficient because a poor edit does not reveal whether additional optimization should place more emphasis on the planner or the renderer, and even planner-dominant cases remain difficult to localize within a free-form reasoning trace. We present DARS, a reinforcement learning framework for dual-level credit assignment in this two-stage setting. Across modules, multi-plan multi-render rollouts estimate between-plan and within-plan reward variability for soft module routing, while rollout mean rewards provide hardness estimates for an adaptive curriculum. Within the planner, a four-field structured reasoning output enables a prefix-gated reward and token-level advantage reweighting, turning outcome-level feedback into localized supervision. Experiments on five benchmarks show that DARS outperforms a Joint~RL baseline with the same backbone, data, reward model, and rollout budget, with the largest gains on reasoning-intensive edits.