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

Source: [ANCHOR: Agentic Noise Creation Framework for Human Simulation and Denoising Recommendation](<https://www.sota2.com/research/paper/6a22589786173ad9c1468b19>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-08-05T05:00:12.726Z

Authors: Xiangming Li, Hua Chu, Jiaming Liang, Jianan Li, Yangtao Zhou

Published: 2026-06-04T02:46:31.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Denoising Recommendation on DBbook 2014](<https://www.sota2.com/research/sota/denoising-recommendation-on-dbbook-2014.md>): Denoising Recommendation; DBbook 2014; Recall@10: 25.12.

- [Denoising Recommendation on Book-Crossing](<https://www.sota2.com/research/sota/denoising-recommendation-on-book-crossing.md>): Denoising Recommendation; Book-Crossing; Recall@10: 0.1084.

- [Denoising Recommendation on MovieLens 1M](<https://www.sota2.com/research/sota/denoising-recommendation-on-movielens-1m.md>): Denoising Recommendation; MovieLens 1M; Recall@10: 20.15.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.05621>)

[PDF](<https://arxiv.org/pdf/2606.05621.pdf>)
