# What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems

arXiv: https://arxiv.org/abs/2608.07565 · HTML: https://mlsanity.com/paper/2608.07565/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 3 Aug 2026.

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback](https://mlsanity.com/paper/2312.00849/) (2023)
- [Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering](https://mlsanity.com/paper/1712.00377/) (2017)
- [GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization](https://mlsanity.com/paper/2601.05242/) (2026)
- [Unbiased Learning-to-Rank with Biased Feedback](https://mlsanity.com/paper/1608.04468/) (2016)
- [ODIN: Disentangled Reward Mitigates Hacking in RLHF](https://mlsanity.com/paper/2402.07319/) (2024)
- [RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness](https://mlsanity.com/paper/2405.17220/) (2024)
- [A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestion](https://mlsanity.com/paper/1507.02221/) (2015)
- [Unbiased Learning to Rank with Unbiased Propensity Estimation](https://mlsanity.com/paper/1804.05938/) (2018)
- [See, Say, and Segment: Teaching LMMs to Overcome False Premises](https://mlsanity.com/paper/2312.08366/) (2023)
- [Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting](https://mlsanity.com/paper/2509.11452/) (2025)
- [MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems](https://mlsanity.com/paper/2509.22047/) (2025)
- [Post-training Large Language Models for Diverse High-Quality Responses](https://mlsanity.com/paper/2509.04784/) (2025)
- [MIRA: Multimodal Iterative Reasoning Agent for Image Editing](https://mlsanity.com/paper/2511.21087/) (2025)
- [CTR-Guided Generative Query Suggestion in Conversational Search](https://mlsanity.com/paper/2507.04072/) (2025)
- [From Clicks to Preference: A Multi-stage Alignment Framework for Generative Query Suggestion in Conversational System](https://mlsanity.com/paper/2508.15811/) (2025)
- [From Prompting to Alignment: A Generative Framework for Query Recommendation](https://mlsanity.com/paper/2504.10208/) (2025)
- [Empowering Visual Creativity: A Vision-Language Assistant to Image Editing Recommendations](https://mlsanity.com/paper/2406.00121/) (2024)
- [DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning](https://mlsanity.com/paper/2605.25604/) (2026)
- [Uncovering Cross-Objective Interference in Multi-Objective Alignment](https://mlsanity.com/paper/2602.06869/) (2026)
- [IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters](https://mlsanity.com/paper/2604.18375/) (2026)
- [OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations](https://mlsanity.com/paper/2605.23668/) (2026)

## Built on by (most cited first, 2 of 2)

- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [Learning to Simulate Individuals from Macro Social Signals](https://mlsanity.com/paper/2610.07062/) (2026)

## Abstract (arXiv)

Conversational assistants increasingly recommend follow-up edits to help users continue a task. Existing systems primarily target text-only interactions, leaving image-creation conversations underexplored. In image-creation tasks, useful follow-up edit suggestions must reflect user preferences, offer diverse directions, and remain executable on the current image. We collected 100,000 real multi-turn image-creation conversation samples from Qwen App and found that 80.1% are image-dependent, underscoring the need for multimodal recommendation. We address this setting with a three-stage framework. In Stage 1, we use real online data to build a human-reviewed table of appropriate follow-up editing intents, then create SFT targets and fine-tune a multimodal policy. In Stage 2, to align rule-guided SFT suggestions with actual user choices, we use user click feedback to optimize the policy through multi-objective reinforcement learning. In Stage 3, to reduce visual inconsistencies between suggested edits and the current image, we introduce a visual verifier as additional training supervision. Extensive experiments demonstrate that our framework significantly outperforms baselines on both automatic and human evaluations. In a live user-randomized A/B test with millions of users, our final framework reduces visual inconsistency from 3.7% to 0.9%. Furthermore, it significantly improves recommendation CTR by 32.70%, image take-away rate by 16.32%, and average conversation turns per user by 39.90% (all p<0.05). Project page: https://what-to-edit-next.github.io/