arXiv:2607. 10541v1 Announce Type: cross Abstract: Sequential recommender systems typically infer user preferences through single-pass encoding of interaction histories without iterative refinement, relying on increasingly deep architectures to capture complex patterns.
arXiv:2607. 29241v1 Announce Type: cross Abstract: Optimizing modern recommender models still depends heavily on engineers manually iterating over architectural, objective, and training-strategy changes.
Auto-RecSys is an autonomous research system designed to scale long-horizon experimentation for industry‑scale recommendation models. It tackles long feedback loops and system complexity by enabling distributed asynchronous execution, centralized cross‑server memory, and a cognitive‑procedural separation that combines natural‑language skill files with deterministic scripts. The system incorporates a dual‑loop self‑evolving architecture—Execution Evolution and Idea Evolution loops—to refine operational playbooks and guide future experiments, thereby reducing human effort per cycle and improving reliability as playbooks mature.
arXiv:2609.34404v2 Announce Type: replace-cross Abstract: Leveraging the strong generative capabilities and stable training dynamics of diffusion models, diffusion-based recommender systems (RSs) hav...
Large language models (LLMs) increasingly shape recommendations across chatbots, e-commerce, and user-generated content (UGC) platforms, creating demand for Generative Engine Optimization (GEO) to imp...
Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems introduces AgentX-Model, a dual-agent framework that links proposal development with model experimentation in business-defined sandboxes. The Research Agent drafts proposals from literature and findings, while the Model Agent runs multi‑round experiments, returning code, metrics, and open questions. The framework cycles through Reproduce, Follow‑up, Composition, and Diagnose actions, achieving high AUC gains and significant business metric improvements in online A/B tests.
AutoRecLab is a Python-based autonomous laboratory for recommender‑system research that transforms natural‑language prompts into executable experiments. It automatically derives experiment requirements, builds and validates prototypes, and iteratively expands them into full studies using retrieval‑augmented generation, static type verification, and execution‑steered tree search. In a demonstration, AutoRecLab autonomously conducted an explicit‑to‑implicit feedback conversion study, achieving 8 of 9 successful runs at an average cost of about $1 per run with GPT‑5.4‑mini.
This reproducibility study investigates the counterfactual explanation method Learning to eXplain Recommendations (LXR) by extending its application beyond the top‑ranked item to other recommended items. The authors compare LXR against alternative baselines such as item popularity and latent factor similarity, noting that these baselines perform surprisingly well on certain tasks. They also analyze how item popularity affects explanation quality, finding that LXR produces shorter perturbations for less popular items, and conduct a brute‑force search to estimate a lower bound on optimal perturbation size.
RPCBench is a new benchmark designed to evaluate large language models’ ability to critique recommendation requests by detecting, diagnosing, and handling flawed premises. It includes evidence‑grounded test instances across five recommendation domains and ten types of premise failures, and introduces a fine‑grained evaluation framework covering detection, error localization, handling strategy, and evidence faithfulness. Experiments with 11 LLMs reveal that proactive detection is the main bottleneck, with models struggling most on underspecified‑premise errors and showing that optimal critique quality occurs at intermediate reasoning lengths.
arXiv:2608. 04625v1 Announce Type: new Abstract: Industrial recommendation strategy iteration heavily relies on large-scale A/B experimentation.
The paper investigates positional bias in large language model (LLM)–based recommender systems that use retrieval‑augmented generation (RAG). It introduces two statistical detection methods—POB‑ICM and POB‑UNBP—to test whether the recommended item depends on the order of candidates in the prompt. Experiments on a product‑recommendation testbed with 40,000 instances show that all evaluated state‑of‑the‑art models exhibit significant positional bias, quantified by new metrics such as permutation sensitivity and strong positional bias, and that this bias is structural and model‑dependent rather than an artifact of decoding or candidate‑set size.
arXiv:2607. 13418v1 Announce Type: cross Abstract: Recommender systems operate as Black-Boxes, leaving users and regulators unable to steer their outputs toward specific intentions or audit their behavior.