arXiv:2606. 10129v1 Announce Type: new Abstract: While deep Reinforcement Learning (deep-RL) has been increasingly applied to parameter control in evolutionary algorithms, rigorous theoretical analysis of parameter control remains largely restricted to single-parameter settings, owing to the difficulty of deriving effective, interpretable multi-parameter policies amenable to formal study.
By Tai Nguyen, Phong Le, Carola Doerr, Nguyen Dang
arXiv:2607. 18252v1 Announce Type: new Abstract: Machine learning methods have shown that data-driven policies can accelerate mixed-integer linear programming (MILP) solvers, but many such approaches remain difficult to inspect, adapt, and deploy because the learned policy is represented as an external predictor or other opaque model.
By Jinbiao Nie, Kewei Feng, Xiaoyuan Zhang, Shan Yin, Zizhuo Wang, Bin Dong
arXiv:2507. 04136v2 Announce Type: replace Abstract: This survey offers a comprehensive foundation on the integration of RL with language models, highlighting prominent algorithms such as Proximal Policy Optimization (PPO), Q-Learning, and Actor-Critic methods.
By Saksham Sahai Srivastava, Vaneet Aggarwal
arXiv:2607. 02390v1 Announce Type: new Abstract: How can Large Language Models (LLMs) solve problems they currently cannot?
By Juliette Decugis, Fabian Gloeckle, Francis Bach, Taco Cohen, Gabriel Synnaeve
arXiv:2606. 16496v1 Announce Type: cross Abstract: Large multimodal language models (LLMs) have emerged as powerful tools for guiding evolutionary search toward interpretable programmatic policies.
By Pan Wang
arXiv:2602. 03542v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are trained and tested extensively on symbolic representations such as code and graphs, yet real-world user tasks are often specified in natural language.
By Fangru Lin, Valentin Hofmann, Xingchen Wan, Weixing Wang, Zifeng Ding, Anthony G. Cohn, Janet B. Pierrehumbert
arXiv:2604. 08324v3 Announce Type: replace-cross Abstract: Symbolic regression (SR) aims to discover mathematical expressions from data, a task traditionally tackled using Genetic Programming (GP) through combinatorial search over symbolic structures.
By Benjamin L\'eger, Kazem Meidani, Christian Gagn\'e
The paper introduces Reinforcement Learning Enhanced LLM Agents (RLEA), a multi‑agent framework that automates the modeling of complex Vehicle Routing Problems (VRPs). RLEA employs a lightweight neural Planner trained with Soft Q‑learning to coordinate LLM‑based agents, and incorporates an evolutionary memory module and retrieval‑augmented generation to leverage experience and external solver knowledge. Experiments on 48 VRP variants show that RLEA outperforms the prior state‑of‑the‑art method, achieving a 16.67% higher success rate and significantly reducing runtime errors.
By Yi Chen, Zikang Yu, Jiahai Wang, Jinbiao Chen, Jianpeng Zhou, Zizhen Zhang
Collab‑Solver introduces a multi‑agent policy learning framework for mixed‑integer linear programming (MILP) that enables collaborative optimization of multiple solver modules. By modeling the interaction between cut selection and branching as a Stackelberg game, the approach employs a two‑phase learning paradigm—data‑communicated policy pretraining followed by coordinated policy refinement. Experiments on synthetic and large‑scale real‑world MILP datasets show that the jointly learned policies markedly improve solving performance and generalize well across diverse instance sets.
By Siyuan Li, Yifan Yu, Zhihao Zhang, Mengjing Chen, Fangzhou Zhu, Tao Zhong, Peng Liu, Jianye Hao
arXiv:2607. 00531v1 Announce Type: cross Abstract: Scientific reasoning is an increasingly important capability of large language models, yet improving the robustness and efficiency of training such reasoning remains a key open challenge.
By Xuefeng Liu, Mingxuan Cao, Qinan Huang, Thomas Brettin, Rick Stevens, Le Cong
The paper introduces HOW TO TRAIN YOUR LITTLE DRAGON, a method for teaching a small language model to generate and refine GPU optimization scripts. Using a compact, lossless representation of compiler traces, the authors train the model on 108,594 examples derived from TVM MetaSchedule, first with supervised fine‑tuning and then with reinforcement learning that rewards correctness and performance. After training, an 8‑billion‑parameter model achieves over 91% correctness in both construction and refinement tasks and outperforms several much larger LLMs on kernel performance.
By Annabelle Sujun Tang, Wei Tang, Songyao Jiang, Tianhui Li, Shengzhe Xu, Jiin Woo, Kaan Ozkara, Youngsuk Park, Zhen Jia, Hadi Esmaeilzadeh
CoDA is a framework that lets a simulation data engine and an action policy evolve together using a shared memory of environment construction, policy failures, and learning progress. The memory stores validated diagnoses from a vision‑language critic, which are turned into generation programs that recreate challenging scenarios and training programs that help the policy improve. Using this approach, CoDA boosts out‑of‑distribution success on several manipulation tasks, raising success rates from 5.3 % to 27.6 % and achieving up to 84 % success on LIBERO‑Pro under perturbations.
By Tianjiao Yu, Zhilin Ou, Yifan Shen, Xinzhuo Li, Yuanzhe Liu, Onkar Kishor Susladkar, Fan Wang, Ismini Lourentzou