Lune

ICML2026Top-tier venue

EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions

Xiyuan Zhou, Ruixi Zou, Xinlei Wang, Yuheng Cheng, Yan Xu, Junhua Zhao, Jinjin Gu

Abstract

Engineering problem solving is central to real-world decision-making, requiring mathematical formulations that not only represent complex problems but also produce feasible solutions under data and physical constraints. Unlike mathematical problem solving, which operates on predefined formulations, engineering tasks demand open-ended analysis, feasibility-driven modeling, and iterative refinement. Although large language models (LLMs) have shown strong capabilities in reasoning and code generation, they often fail to ensure feasibility, which limits their applicability to engineering problem solving. To address this challenge, we propose EngiAgent, a multi-agent system with a fully connected coordinator that simulates expert workflows through specialized agents for problem analysis, modeling, verification, solving, and solution evaluation. The fully connected coordinator enables flexible feedback routing, overcoming the rigidity of prior pipeline-based reflection methods and ensuring feasibility at every stage of the process. This design not only improves robustness to diverse failure cases such as data extraction errors, constraint inconsistencies, and solver failures, but also enhances the overall quality of problem solving. Empirical results across four representative domains demonstrate that EngiAgent achieves substantial improvements in feasibility compared to prior approaches, establishing a new paradigm for feasibility-oriented engineering problem solving with LLMs. Our source code and data are available at https://github.com/AI4Engi/EngiAgent.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Agent Laboratory: Using LLM Agents as Research Assistants cites MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
  • Agent Laboratory: Using LLM Agents as Research Assistants cites DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
  • Executable Code Actions Elicit Better LLM Agents cites PAL: Program-aided Language Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on9

  1. PAL: Program-aided Language ModelsLuyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon et al.ICML 2023 · 700 citations
  2. Executable Code Actions Elicit Better LLM AgentsXingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang et al.ICML 2024 · 436 citations
  3. MLAgentBench: Evaluating Language Agents on Machine Learning ExperimentationQian Huang, Jian Vora, Percy Liang, Jure LeskovecICML 2024 · 209 citations
  4. DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based ReasoningSiyuan Guo, Cheng Deng, Ying Wen, Hechang Chen et al.ICML 2024 · 107 citations
  5. Agent Laboratory: Using LLM Agents as Research AssistantsSamuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun et al.EMNLP Findings 2025 · 60 citations

Related papers

  1. EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem SolvingXiyuan Zhou, Xinlei Wang, Yirui He, Ruixi Zou et al.ACL Findings 2026 · 2 citations
  2. Chain-of-Experts: When LLMs Meet Complex Operations Research ProblemsZiyang Xiao, Dongxiang Zhang, Yangjun Wu, Lilin Xu et al.ICLR 2024 · 136 citations
  3. Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHubBohan Lyu, Xin Cong, Heyang Yu, Pan Yang et al.ACL 2025
  4. BOAD: Discovering Hierarchical Software Engineering Agents via Bandit OptimizationIris Xu, Guangtao Zeng, Zexue He, Charles Jin et al.ICLR 2026 · 5 citations
  5. Agent-Based Ensemble Reasoning for Repository-Level Issue ResolutionZhao Tian, Pengfei Gao, Junjie Chen, Chao PengICSE 2026
Dusk over the sea between two cliffs drawn in fine vertical lines