Alibaba's RecGPT-Mobile-V2: On-Device Behavior Prediction with RL
_reachsumit · x · 2026-08-26
Alibaba released the RecGPT-Mobile-V2 technical report, detailing an end-to-end on-device framework that predicts a user's next search query from behavior. Addressing on-device challenges like noisy trajectories and limited compute budgets, the framework:
- Transforms heterogeneous interactions into evidence-preserving trajectories.
- Establishes a recommendation-native foundation via domain adaptation and supervised alignment.
- Applies reasoning-cost optimization only after grouped rollouts meet grounding and utility criteria.
- Distills the teacher model into a compact student model using low-bit execution, structured compression, and budget-aware device-cloud routing.
Experiments show it cuts unnecessary reasoning while preserving accuracy.
More from Infra
- Japanese Firms to Host FOUND Workshop at ECCV 2026 Focusing on Foundation Data — HirokatuKataoka · 2026-08-26
- Reproducing GPT-2 now costs $48, putting superhuman AI under $500 — jennyzhangzt · 2026-08-26
- Tune AMD V620 power/clock on Windows without VBIOS flashing — Brave_Load7620 · 2026-08-26
- Akta launches Company Data API for AI Agents with entity resolution — AppropriateAnt7344 · 2026-08-26
- AMD MI350X Runs Qwen3.6-35B: Open Source Kernel Achieves 78.5k tok/s on 8 GPUs — SmilingGen · 2026-08-26
- MetricFire releases MCP server to query monitoring data with AI tools — PKMNPinBoard · 2026-08-26