Entity · technique

Identity Preference Optimization

techniqueactiveprovisionalidentity-preference-optimization-0215e117·1 events·first seen 2d ago

Aliases: Identity Preference Optimization

Co-occurring entities

Large Language Model for Operations Research Formulation Selection in Multi-Warehouse Inventory Allocation GRPO (Group Relative Policy Optimization)JD.com

More like this (12)

Drifting Preference Optimization Direct Preference Optimization (DPO)Gravity-Weighted Direct Preference Optimization Role-Aware Policy Optimization Hierarchical Relative Policy Optimization General Preference Model REAR: Test-time Preference Realignment through Reward Decomposition Freeform Preference Learning Vector Policy Optimization Atomic Policy Optimization Adaptive Clip Policy Optimization Grounded Context Preference Dataset

Recent events (1)

5arXiv · cs.AI·2d ago·source ↗

LLM framework for instance-wise OR formulation selection improves multi-warehouse inventory allocation at JD.com

Researchers propose a solver-guided LLM framework that selects among a library of MIP formulations for multi-warehouse inventory allocation on a per-instance basis, rather than applying a single fixed formulation. The system is trained via SFT, IPO preference optimization, and GRPO reinforcement learning using MIP solver evaluations as reward signals. Evaluated on real JD.com data, GRPO raises Hit Ratio@1 from 21.45% to 50.42% and achieves a 12.57 percentage point allocation accuracy gain over the incumbent baseline. The work demonstrates a practical pattern of using LLMs as meta-selectors over classical OR solvers in industrial logistics settings.

Enterprise Deployment Patterns Agent and Tool Ecosystem Large Language Model for Operations Research Formulation Selection in Multi-Warehouse Inventory Allocation Identity Preference Optimization GRPO (Group Relative Policy Optimization)+1 more