AI & ML
RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems
arXiv cs.IR0 views
arXiv:2607.29241v2 Announce Type: replace Abstract: Optimizing recommender models remains heavily reliant on manual iteration over architectures, objectives, and training strategies. While LLM-based agents can automate this trial-and-error process, relying on LLMs to both select modification directions and formulate concrete hypotheses can lead to unstable search under limited trial budgets. Inspired by the above challenge, we propose RecHarness, a Bandit-Routed Agentic Harness for automated recommender model optimization. RecHarness decouples 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 consistent performance improvements and uses limited trial budgets more effectively than LLM-directed 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.
Source:https://arxiv.org/abs/2607.29241PreviousBeyond Retrieval: Learning Compact User Representations for Scalable LLM PersonalizationNextCodeHID: Learning an Addressable Hierarchical Code Index for Generative Code Retrieval
Related posts

Do cybersecurity certifications raise pay? Postings that name one advertise 13.8% less (Nov 2026)
0dev.to Security
Ninety Days Became Thirty: What the Disclosure Deadline Collapse Actually Teaches
0dev.to Security

Make your voice count in the State of Observability & Reliability report
0dev.to DevOps
config init container for Nsigth Command
0dev.to Docker

Anthropic IPO is set to redraw VC power rankings, with lesser-known firms like Spark Capital poised for outsized returns compared with larger, blue-chip rivals (George Hammond/Financial Times)
0Techmeme

A Gallup survey of 15,925 people aged 15 to 22 across 16 countries finds that more than 33% rely on AI for companionship, rising to 50% among daily AI users (Jason Parham/Wired)
0Techmeme