2026/02/28 by Qi Liu, Ruochen Hao, Can Li +1
Computer Science · #cs.AI #cs.CE #cs.NE
paper · pdf · doi:10.48550/arxiv.2602.13769
arxiv created 2026/08/04 · arxiv updated 2026/08/05
Automating heuristic design in complex, experiment-driven domains requires more than iterative mutation of solution algorithms. Current LLM-based evolutionary methods often rely on stochastic mutation loops that lack long-term strategic planning and a formal mechanism to learn from historical failures, leading to inefficient exploration and redundant trials. To address this, we present OR-Agent, a multi-agent research framework designed for automated heuristic design in optimization problems with rich experimental environments. OR-Agent organizes heuristic search as tree-based workflow that explicitly models branching hypothesis generation and systematic backtracking. Furthermore, to address the lack of adaptive learning in current agents, we introduce a hierarchical, optimization-inspired reflection system in which short-term reflections act as verbal gradients, long-term reflections as verbal momentum, and memory compression as semantic weight decay - collectively forming a principled mechanism for governing research dynamics. Extensive experiments on classical combinatorial optimization problems (e.g., TSP, CVRP, bin packing) and simulation-based cooperative driving scenarios demonstrate that OR-Agent outperforms strong evolutionary search baselines. All code and experimental data are publicly available at https://github.com/qiliuchn/OR-Agent.