# Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems

arXiv: https://arxiv.org/abs/2609.30001 · HTML: https://mlsanity.com/paper/2609.30001/

## 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 33 of its 34 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Placed in

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

## Builds on (most cited first, 30 of 33)

- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench](https://mlsanity.com/paper/2507.02554/) (2025)
- [An AI system to help scientists write expert-level empirical software](https://mlsanity.com/paper/2509.06503/) (2025)
- [RankMixer: Scaling Up Ranking Models in Industrial Recommenders](https://mlsanity.com/paper/2507.15551/) (2025)
- [SkillGen: Verified Inference-Time Agent Skill Synthesis](https://mlsanity.com/paper/2605.10999/) (2026)
- [MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery](https://mlsanity.com/paper/2606.06473/) (2026)
- [Differentiable Semantic ID for Generative Recommendation](https://mlsanity.com/paper/2601.19711/) (2026)
- [Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents](https://mlsanity.com/paper/2602.10226/) (2026)
- [Dream-RSI: Recursive Self-Improvement through Evolving Worlds](https://mlsanity.com/paper/2609.14858/) (2026)
- [Toward Autonomous Long-Horizon Engineering for ML Research](https://mlsanity.com/paper/2604.13018/) (2026)
- [HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?](https://mlsanity.com/paper/2609.01437/) (2026)
- [AI Research Preference Models](https://mlsanity.com/paper/2608.13940/) (2026)
- [Climber: Toward Efficient Scaling Laws for Large Recommendation Models](https://mlsanity.com/paper/2502.09888/) (2025)
- [UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems](https://mlsanity.com/paper/2604.00590/) (2026)
- [FuXi-β: Towards a Lightweight and Fast Large-Scale Generative Recommendation Model](https://mlsanity.com/paper/2508.10615/) (2025)
- [NOVA: A Verification-Aware Agent Harness for Architecture Evolution in Industrial Recommender Systems](https://mlsanity.com/paper/2606.27243/) (2026)
- [SMES: Towards Scalable Multi-Task Recommendation via Expert Sparsity](https://mlsanity.com/paper/2602.09386/) (2026)
- [ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond](https://mlsanity.com/paper/2608.14354/) (2026)
- [PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents](https://mlsanity.com/paper/2608.26530/) (2026)
- [DOS: Dual-Flow Orthogonal Semantic IDs for Recommendation in Meituan](https://mlsanity.com/paper/2602.04460/) (2026)
- [RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems](https://mlsanity.com/paper/2607.29241/) (2026)
- [Agora: Git as Shared Memory for Collective AutoResearch](https://mlsanity.com/paper/2609.18094/) (2026)
- [Astar: Learning to Propose Evolution Directions for Self-Evolving Industrial AI Systems](https://mlsanity.com/paper/2608.27287/) (2026)
- [CORAL: An LLM-Native Harness for Production Recommender Systems](https://mlsanity.com/paper/2609.02730/) (2026)
- [From Clues to Generation: Language-Guided Conditional Diffusion for Cross-Domain Recommendation](https://mlsanity.com/paper/2604.05365/) (2026)
- [Memory Is No Longer a Bottleneck: Memory-Efficient Graph Filtering for Scalable Collaborative Filtering](https://mlsanity.com/paper/2606.21540/) (2026)
- [TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems](https://mlsanity.com/paper/2606.25147/) (2026)
- [From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents](https://mlsanity.com/paper/2608.05235/) (2026)
- [RecSys Factory: Bounding LLM Agent Autonomy to Decision Points in the Industrial Recommender Lifecycle](https://mlsanity.com/paper/2608.11241/) (2026)
- [RecEvolve: A Knowledge-Driven Autonomous Agent System for Recommender Systems](https://mlsanity.com/paper/2609.01622/) (2026)

## Abstract (arXiv)

Sustaining industrial recommendation research requires using the results of one experiment to decide what to investigate next. We present AgentX-Model, the next generation of AgentX's model research framework, which connects proposal development and model experimentation within sandboxes defined by business inputs and prediction tasks. AgentX-Model adopts a dual-agent architecture comprising a Research Agent and a Model Agent. The Research Agent develops independently reviewed proposals from papers and experimental findings, while the Model Agent conducts multi-round investigations and returns code, measurements, and unresolved questions. Using the returned results, the Research Agent selects a starting implementation and formulates the next research question, allowing subsequent experiments to build on earlier findings. We organize this continuing research around four actions: Reproduce, Follow-up, Composition, and Diagnose. The first three actions drive routine research, while Diagnose acquires the evidence needed to choose a repair, including for issues raised by business feedback and online evaluation, such as prediction bias measured by PCOC. Across the production evaluation, 560 of 636 completed model-changing experiments recorded AUC above their business baselines. As research continued, some experiments recorded AUC above every comparable ancestor in their lineages. The five latest online A/B evaluations across different business settings reported gains including 10-15% in acquisition efficiency, 15-20% in target-segment advertising spend, and 0.3-0.8% in watch time; the watch-time model used approximately 10% fewer FLOPs and parameters. A dependency-aware historical-replay benchmark further evaluates research allocation, with initial results showing no consistent efficiency gain from more complex scheduling when agents already analyze and select concrete candidates.