# RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems

arXiv: https://arxiv.org/abs/2607.29241 · HTML: https://mlsanity.com/paper/2607.29241/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 37 of its 44 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 30 of 37)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions](https://mlsanity.com/paper/2006.02903/) (2020)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations](https://mlsanity.com/paper/2402.17152/) (2024)
- [Neural Architecture Optimization](https://mlsanity.com/paper/1808.07233/) (2018)
- [A Simple Convolutional Generative Network for Next Item Recommendation](https://mlsanity.com/paper/1808.05163/) (2018)
- [KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems](https://mlsanity.com/paper/2202.10842/) (2022)
- [Can large language models explore in-context?](https://mlsanity.com/paper/2403.15371/) (2024)
- [AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench](https://mlsanity.com/paper/2507.02554/) (2025)
- [MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement](https://mlsanity.com/paper/2506.15692/) (2025)
- [LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders](https://mlsanity.com/paper/2505.04421/) (2025)
- [Deconfounding Duration Bias in Watch-time Prediction for Video Recommendation](https://mlsanity.com/paper/2206.06003/) (2022)
- [AutoLoss: Automated Loss Function Search in Recommendations](https://mlsanity.com/paper/2106.06713/) (2021)
- [AutoField: Automating Feature Selection in Deep Recommender Systems](https://mlsanity.com/paper/2204.09078/) (2022)
- [AutoML for Deep Recommender Systems: A Survey](https://mlsanity.com/paper/2203.13922/) (2022)
- [Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents](https://mlsanity.com/paper/2602.10226/) (2026)
- [Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation](https://mlsanity.com/paper/2306.03392/) (2023)
- [Generative Regression Based Watch Time Prediction for Short-Video Recommendation](https://mlsanity.com/paper/2412.20211/) (2024)
- [Memorize, Factorize, or be Na"ive: Learning Optimal Feature Interaction Methods for CTR Prediction](https://mlsanity.com/paper/2108.01265/) (2021)
- [Lost in Sequence: Do Large Language Models Understand Sequential Recommendation?](https://mlsanity.com/paper/2502.13909/) (2025)
- [AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems](https://mlsanity.com/paper/2606.26859/) (2026)
- [Structured Spectral Reasoning for Frequency-Adaptive Multimodal Recommendation](https://mlsanity.com/paper/2512.01372/) (2025)

## Built on by (most cited first, 3 of 3)

- [AutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems](https://mlsanity.com/paper/2609.04871/) (2026)
- [Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems](https://mlsanity.com/paper/2609.30001/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

Optimizing modern recommender models still depends heavily on engineers manually iterating over architectural, objective, and training-strategy changes. While LLM-based agents can automate this trial-and-error process, allowing the LLM to both select modification directions and generate concrete hypotheses often leads to unstable search under limited experiment budgets. Inspired by the above challenge, we propose RecHarness, a Bandit-Routed Agentic Harness for automated recommender model optimization. RecHarness separates the optimization process into two steps: a bandit router selects the next modification direction according to historical validation feedback, while the LLM generates a concrete optimization hypothesis and executable code edit within the selected direction. To sustain long-horizon exploration, RecHarness uses a jump-basin mechanism to activate a structural-jump arm when local edits stagnate. Across multiple recommendation tasks, datasets, and model backbones, RecHarness achieves more stable performance improvements and uses limited trial budgets more effectively than LLM-reasoning search. During a 7-day online A/B test on a large-scale short-video advertising platform, the selected candidate improves ADVV by 2.084%, Revenue by 0.534%, and Exposure by 0.559%. Code is available at https://github.com/6lyc/RecHarness.