Google's RPTune Boosts In-Context Catalog Search Accuracy by Up to 31.4 Points
google · hf · 2026-10-02
Google proposes RPTune, an end-to-end framework for in-context catalog search: for SMBs whose catalogs fit a long-context LLM, it couples learned catalog curation—an encoder-reorganizer that orders and prunes products guided by downstream LLM feedback—with LLM post-training using catalog-grounded, context-relative rewards. Across 7 real merchants and 100 complex conversational queries each, curation yields gains up to 31.4 percentage points and post-training adds 10.3 on average, consistently improving both proprietary and open-weight LLMs.
Related event: Google's RPTune boosts LLM catalog search accuracy by up to 31.4 points(2 posts)→
More from Research
- Adaptive effort is likely the killer app for dynamic looped transformers — willcb · 2026-10-02
- HuST Lab's Multimodal Flow: Fully Continuous Unified Language-Vision Generation — hustvl · 2026-10-02
- Kuaishou's DARA Cuts Multi-Reward RL Training Steps by Up to 65% — kuaishou · 2026-10-02
- Argo-Bench Pits Data Agents Against a 7.5B-Row Warehouse; Best Model Clears Only 34.8% of Tasks — textql · 2026-10-02
- LoopCD: training-free contrastive decoding lifts looped transformers, AIME 61.9%→73.3% — arankomatsuzaki · 2026-10-02
- Is Jev secretly learning a Value function? RL calibration and System 1/2 — lateinteraction · 2026-10-02