SyncAI.news, a Varaisys broadcasting
LLMs as Adaptive Meta-Solvers: Strategy-Diverse RL for Industrial-Scale Optimization
SZ

Shihao Zhang, Weiting Liu, Siyu Shao, Yitian Chen, Jianfeng Feng, Dongdong Ge, Yinyu Ye

· 1 min read

ResearcharXiv cs.CL

LLMs as Adaptive Meta-Solvers: Strategy-Diverse RL for Industrial-Scale Optimization

arXiv:2609.34427v1 Announce Type: cross Abstract: Scaling LLM-based optimization from textbook-scale instances to real-world, industrial tasks remains a critical open challenge. Existing approaches are predominantly evaluated on small, self-contained textual problems and often commit to a solver-integrated paradigm, limiting their ability to handle the scale and structural diversity of practical optimization workloads. In this work, we propose a practical framework for training open-source LLMs to tackle real-world, industrial-scale optimization. We first show empirically that solver-integrated reasoning, exact combinatorial algorithm, and heuristic search exhibit complementary strengths across different problem structures and scales. Motivated by this, we introduce Strategy-Diverse Reinforcement Learning (SDRL), which trains LLMs as adaptive optimization meta-solvers. SDRL leverages this complementarity through a correctness-gated hierarchical diversity reward that promotes robust exploration across varying strategies and within each strategy, effectively preventing premature strategy collapse. We further introduce a mixed-format training scheme that jointly supports both self-contained textual problems and file-grounded instances. Across comprehensive evaluations, our framework outperforms existing fine-tuned methods and frontier models including DeepSeek-V4-Pro and GPT-5.5, both on average across benchmarks and on industrial-scale optimization tasks.

Original source

This story was published by arXiv cs.CL and written by Shihao Zhang, Weiting Liu, Siyu Shao, Yitian Chen, Jianfeng Feng, Dongdong Ge, Yinyu Ye. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News