Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

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

First seen · 7/31/2026, 04:00 AMLatest activity · 7/31/2026, 04:00 AM

RecHarness is an agentic framework for automating recommender-model optimization. It separates search-direction selection from hypothesis and code generation: a bandit router chooses among modification directions using historical validation feedback, while an LLM proposes a concrete optimization and executable code edit within the selected direction. A structural-jump arm is activated when local edits stagnate, supporting longer-horizon exploration. The paper reports more stable gains and better use of limited trial budgets than LLM-reasoning search across recommendation tasks, datasets, and backbones, and mentions a seven-day online A/B test on a large-scale short-video advertising platform. The supplied abstract is truncated, so the online-test metrics are unavailable here.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorHuggingFace Daily Papers7/31, 04:00 AMnot independentRepresentative
    RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems