Industrial Technology and Control Systems

Latest papers

• Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents

  Huaiyu Fu, Heng Cao, Hao Wang, Jian Ya, Tao Chen · 1 October 2026

  LLM agents often admit multiple high-quality solutions to the same task, differing in reasoning structure, tool-use pattern, or interaction trajectory. Yet existing notions of diversity in LLM post-training are mostly implicit, arising from general stochasticity and regularization mechanisms rather …

• Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training

  Junwon Ko, Dong-Jae Lee, Minchan Kwon, Sunghyun Baek, Junmo Kim · 10 September 2026

  LLM agents for sequential decision tasks are often post-trained with trajectory-level outcome labels, but such labels provide little supervision for preserving multiple successful branches from the same decision state. We study this problem as successful strategy coverage: how broadly a model realiz…

• SRPO: Setwise Relative Policy Optimization for Multi-Agent LLMs

  Shengtian Yang, Ziyu Xiong, Yu Li, Yewen Li, Qingpeng Cai, Lei Feng · 9 September 2026

  Multi-agent large language models solve complex tasks by coordinating several policies in a shared environment. However, existing reinforcement learning methods usually optimize each response or trajectory separately, even when several outputs jointly cause one state transition. Consequently, the up…

• Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning

  Oussama Hidaoui, Omer Ebead, Ulrich Armel Mbou Sob, Siddarth Singh, Juan Claude Formanek, Felix Chalumeau, Omayma Mahjoub, Sasha Abramowitz, Ruan John de Kock, Wiem Khlifi, Louay Ben Nessir, Simon Verster Du Toit, Daniel Rajaonarivonivelomanantsoa, Asim Awad Osman, Arnol Manuel Fokam, Refiloe Shabe, Arnu Pretorius · 4 September 2026

  Generalising to unseen tasks remains a fundamental challenge in offline multi-agent reinforcement learning (MARL). In this work, we present a principled analysis of zero-shot task generalisation in the offline setting and conduct an extensive empirical investigation into the scaling behaviour govern…

• WMLLM: Self-Evolving Optimization Agents via Predict-Then-Act World Modeling

  Zhongzheng Li, Qingsong Ran, Shikun Feng, Nian Ran, Wenhao Li, Xiaoyuan Zhang, Yue Wang, Xiaoguang Zhao · 3 September 2026

  Black-box optimization problems remain challenging because of large, weakly structured, and high-dimensional search spaces. Existing methods often suffer from poor sample efficiency because they rely on direct candidate generation or trial-and-error refinement. A natural way to improve search effici…

• Bi-EZP: LLM-Guided Bilevel Program Evolution for Ensemble Zero-Cost Proxy Discovery

  Yutao Lai, Kezhao Lai, Hai-Lin Liu · 25 August 2026

  Zero-cost proxies enable neural architecture search (NAS) to rank candidate networks from statistics computed at initialization, avoiding repeated training. However, different proxies capture different properties and often produce inconsistent rankings across search spaces. Ensemble proxies can comb…

• Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection

  Atsuyuki Miyai, Kiyoharu Aizawa, Toshihiko Yamasaki · 21 August 2026

  We present a novel approach to efficient LLM agent harness optimization through adaptive validation task selection. Harness optimization iteratively rewrites the harness code based on validation performance, enabling substantial performance gains without updating the underlying model weights. Existi…

• Topology Enhanced MARL for Multi-Agent Cooperative Decision-Making of CAVs

  Ye Han, Lijun Zhang, Dejian Meng, Zhuang Zhang · 4 August 2026

  Decentralized multi-agent cooperative decision-making in continuous environments is fundamentally bottlenecked by the curse of dimensionality, where undirected exploration typically converges to conservative local optima. We propose Topology-Enhanced Multi-Agent Reinforcement Learning (TPE-MARL) to …

• End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning

  Guanzhong Chen, Shaoxiong Yang, Chao Li, Wei Liu, Jian Luan, Zenglin Xu · 21 April 2026

  Large language models (LLMs) are versatile, yet their deployment in complex real-world settings is limited by static knowledge cutoffs and the difficulty of producing controllable behavior within a single inference. Multi-agent search systems (MASS), which coordinate specialized LLM agents equipped …

• An Innovative Next Activity Prediction Using Process Entropy and Dynamic Attribute-Wise-Transformer in Predictive Business Process Monitoring

  Hadi Zare, Mostafa Abbasi, Maryam Ahang, Homayoun Najjaran · 8 April 2026

  Next activity prediction in predictive business process monitoring is crucial for operational efficiency and informed decision-making. While machine learning and Artificial Intelligence have achieved promising results, challenges remain in balancing interpretability and accuracy, particularly due to…

• A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism

  Yu Xue, Pengcheng Jiang, Chenchen Zhu, MengChu Zhou, Mohamed Wahib, Moncef Gabbouj · 29 December 2025

  Neural architecture search (NAS) has emerged as a powerful paradigm that enables researchers to automatically explore vast search spaces and discover efficient neural networks. However, NAS suffers from a critical bottleneck, i.e. the evaluation of numerous architectures during the search process de…

• Scaffolded Language Models with Language Supervision for Mixed-Autonomy: A Survey

  Matthieu Lin, Jenny Sheng, Andrew Zhao, Shenzhi Wang, Yang Yue, Victor Shea Jay Huang, Huan Liu, Jun Liu, Gao Huang, Yong-Jin Liu · 5 November 2025

  This survey organizes the intricate literature on the design and optimization of emerging structures around post-trained LMs. We refer to this overarching structure as scaffolded LMs and focus on LMs that are integrated into multi-step processes with tools. We view scaffolded LMs as semi-parametric …

• Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning

  Yuanyao Chen, Rongsheng Chen, Fu Luo, Zhenkun Wang · 31 October 2025

  Neural Combinatorial Optimization (NCO) has emerged as a promising learning-based paradigm for addressing Vehicle Routing Problems (VRPs) by minimizing the need for extensive manual engineering. While existing NCO methods, trained on small-scale instances (e.g., 100 nodes), have demonstrated conside…