# ANCHOR: Agentic Noise Creation Framework for Human Simulation and Denoising Recommendation

arXiv: https://arxiv.org/abs/2606.05621 · HTML: https://mlsanity.com/paper/2606.05621/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 20 of 20)

- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Neural Factorization Machines for Sparse Predictive Analytics](https://mlsanity.com/paper/1708.05027/) (2017)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences](https://mlsanity.com/paper/1902.06236/) (2019)
- [Denoising Implicit Feedback for Recommendation](https://mlsanity.com/paper/2006.04153/) (2020)
- [MACRec: a Multi-Agent Collaboration Framework for Recommendation](https://mlsanity.com/paper/2402.15235/) (2024)
- [A Survey on Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2308.01118/) (2023)
- [A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval](https://mlsanity.com/paper/2503.05659/) (2025)
- [Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System](https://mlsanity.com/paper/2306.09821/) (2023)
- [Self-Guided Learning to Denoise for Robust Recommendation](https://mlsanity.com/paper/2204.06832/) (2022)
- [END4Rec: Efficient Noise-Decoupling for Multi-Behavior Sequential Recommendation](https://mlsanity.com/paper/2403.17603/) (2024)
- [Double Correction Framework for Denoising Recommendation](https://mlsanity.com/paper/2405.11272/) (2024)
- [Learning Robust Recommenders through Cross-Model Agreement](https://mlsanity.com/paper/2105.09605/) (2021)
- [Robust Preference-Guided Denoising for Graph based Social Recommendation](https://mlsanity.com/paper/2303.08346/) (2023)
- [Sampler Design for Bayesian Personalized Ranking by Leveraging View Data](https://mlsanity.com/paper/1809.08162/) (2018)
- [Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment](https://mlsanity.com/paper/2305.05585/) (2023)
- [Unleashing the Power of Large Language Model for Denoising Recommendation](https://mlsanity.com/paper/2502.09058/) (2025)
- [Bridging the User-side Knowledge Gap in Knowledge-aware Recommendations with Large Language Models](https://mlsanity.com/paper/2412.13544/) (2024)
- [RuleAgent: Discovering Rules for Recommendation Denoising with Autonomous Language Agents](https://mlsanity.com/paper/2503.23374/) (2025)

## Abstract (arXiv)

Distilling accurate user preferences from noisy implicit feedback remains a fundamental bottleneck in recommendation systems, highlighting the need for recommendation denoising. However, real-world data lack explicit noise annotations, forcing existing methods to rely on unsupervised side information or handcrafted heuristics. These approaches often incur high external costs, generalize poorly, or depend on unreliable priors, causing noise misidentification and corrupting true user preference representations. To address these limitations, we propose a paradigm-level reformulation of recommendation denoising. Instead of indirectly inferring noisy interactions through heuristics, our Creation-Recognition paradigm proactively creates labeled noisy interactions and trains a dedicated recognizer to identify them, transforming denoising from heuristic filtering into supervised learning. Based on this paradigm, we present ANCHOR, an agent-based framework inspired by recent LLM-as-User research. ANCHOR simulates user behaviors to generate realistic noise labels and enables supervised denoising through two stages: noise creation and noise recognition. In the noise creation stage, ANCHOR adopts a recommender-in-the-loop agentic architecture to synthesize both diverse out-of-preference noise and informative boundary-adjacent noise. For out-of-preference noise, it implements five extensible simulation mechanisms to approximate major sources of noisy implicit feedback. For boundary-adjacent noise, an adversarial boundary refinement mechanism generates ambiguous interactions that challenge the recognizer and target the decision boundary. In the noise recognition stage, ANCHOR leverages the generated labels to train a reusable parametric recognizer that integrates collaborative signals and semantic representations to detect noise patterns in real interaction data.