# NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search

arXiv: https://arxiv.org/abs/2505.14680 · HTML: https://mlsanity.com/paper/2505.14680/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 12 of its 43 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 12 of 12)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [Dense Text Retrieval based on Pretrained Language Models: A Survey](https://mlsanity.com/paper/2211.14876/) (2022)
- [A Deep Relevance Matching Model for Ad-hoc Retrieval](https://mlsanity.com/paper/1711.08611/) (2017)
- [Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era](https://mlsanity.com/paper/2404.11457/) (2024)
- [Comparing Traditional and LLM-based Search for Consumer Choice: A Randomized Experiment](https://mlsanity.com/paper/2307.03744/) (2023)
- [Advancing the Search Frontier with AI Agents](https://mlsanity.com/paper/2311.01235/) (2023)
- [Adaptive Self-Supervised Learning Strategies for Dynamic On-Device LLM Personalization](https://mlsanity.com/paper/2409.16973/) (2024)

## Built on by (most cited first, 4 of 4)

- [Characterizing Web Search in The Age of Generative AI](https://mlsanity.com/paper/2510.11560/) (2025)
- [Learning to Retrieve from Agent Trajectories](https://mlsanity.com/paper/2604.04949/) (2026)
- [How Generative AI Disrupts Search: An Empirical Study of Google Search, Gemini, and AI Overviews](https://mlsanity.com/paper/2604.27790/) (2026)
- [ITER: Interaction-Aware Retrieval for Agentic Search](https://mlsanity.com/paper/2608.27912/) (2026)

## Abstract (arXiv)

Generative AI search is reshaping information retrieval by offering end-to-end answers to complex queries, reducing users' reliance on manually browsing and summarizing multiple web pages. However, while this paradigm enhances convenience, it disrupts the feedback-driven improvement loop that has historically powered the evolution of traditional Web search. Web search can continuously improve their ranking models by collecting large-scale, fine-grained user feedback (e.g., clicks, dwell time) at the document level. In contrast, generative AI search operates through a much longer search pipeline, spanning query decomposition, document retrieval, and answer generation, yet typically receives only coarse-grained feedback on the final answer. This introduces a feedback loop disconnect, where user feedback for the final output cannot be effectively mapped back to specific system components, making it difficult to improve each intermediate stage and sustain the feedback loop. In this paper, we envision NExT-Search, a next-generation paradigm designed to reintroduce fine-grained, process-level feedback into generative AI search. NExT-Search integrates two complementary modes: User Debug Mode, which allows engaged users to intervene at key stages; and Shadow User Mode, where a personalized user agent simulates user preferences and provides AI-assisted feedback for less interactive users. Furthermore, we envision how these feedback signals can be leveraged through online adaptation, which refines current search outputs in real-time, and offline update, which aggregates interaction logs to periodically fine-tune query decomposition, retrieval, and generation models. By restoring human control over key stages of the generative AI search pipeline, we believe NExT-Search offers a promising direction for building feedback-rich AI search systems that can evolve continuously alongside human feedback.