RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experience

Yang Wu, Junran Pan, Yifan Zhang, Ning Xu, Fanshuo Zeng, Jian Cheng
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:136582-136624, 2026.

Abstract

Automatic Heuristic Design (AHD) has emerged as a transformative approach for solving combinatorial optimization problems. While recent Large Language Model (LLM)-based methods have shown promise, they predominantly rely on fixed evolutionary operators and struggle to effectively accumulate and reuse historical search experience. This paper proposes RefineEvo, a novel evolutionary framework that transforms AHD from a static trial-and-error process into a planning-guided, experience-driven system. RefineEvo introduces a Planner to dynamically schedule evolutionary operators and trigger refinement based on the current search state, and a Reflector to distill valuable lessons into a Bidirectional Experience Pool containing both positive insights and negative pitfalls. This synergistic framework enables the system to adapt its search tools to the evolving complexity of the problem and leverage trajectory-aware, situation-conditioned insights to guide generation. Experiments on several classic combinatorial optimization benchmarks demonstrate that RefineEvo consistently outperforms strong baselines. In particular, RefineEvo delivers superior solution quality while improving token efficiency, enabling more efficient and autonomous heuristic design.

Cite this Paper


BibTeX
@InProceedings{pmlr-v306-wu26ap, title = {{R}efine{E}vo: Planning-Guided Heuristic Evolution with Bidirectional Experience}, author = {Wu, Yang and Pan, Junran and Zhang, Yifan and Xu, Ning and Zeng, Fanshuo and Cheng, Jian}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {136582--136624}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/wu26ap/wu26ap.pdf}, url = {https://proceedings.mlr.press/v306/wu26ap.html}, abstract = {Automatic Heuristic Design (AHD) has emerged as a transformative approach for solving combinatorial optimization problems. While recent Large Language Model (LLM)-based methods have shown promise, they predominantly rely on fixed evolutionary operators and struggle to effectively accumulate and reuse historical search experience. This paper proposes RefineEvo, a novel evolutionary framework that transforms AHD from a static trial-and-error process into a planning-guided, experience-driven system. RefineEvo introduces a Planner to dynamically schedule evolutionary operators and trigger refinement based on the current search state, and a Reflector to distill valuable lessons into a Bidirectional Experience Pool containing both positive insights and negative pitfalls. This synergistic framework enables the system to adapt its search tools to the evolving complexity of the problem and leverage trajectory-aware, situation-conditioned insights to guide generation. Experiments on several classic combinatorial optimization benchmarks demonstrate that RefineEvo consistently outperforms strong baselines. In particular, RefineEvo delivers superior solution quality while improving token efficiency, enabling more efficient and autonomous heuristic design.} }
Endnote
%0 Conference Paper %T RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experience %A Yang Wu %A Junran Pan %A Yifan Zhang %A Ning Xu %A Fanshuo Zeng %A Jian Cheng %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-wu26ap %I PMLR %P 136582--136624 %U https://proceedings.mlr.press/v306/wu26ap.html %V 306 %X Automatic Heuristic Design (AHD) has emerged as a transformative approach for solving combinatorial optimization problems. While recent Large Language Model (LLM)-based methods have shown promise, they predominantly rely on fixed evolutionary operators and struggle to effectively accumulate and reuse historical search experience. This paper proposes RefineEvo, a novel evolutionary framework that transforms AHD from a static trial-and-error process into a planning-guided, experience-driven system. RefineEvo introduces a Planner to dynamically schedule evolutionary operators and trigger refinement based on the current search state, and a Reflector to distill valuable lessons into a Bidirectional Experience Pool containing both positive insights and negative pitfalls. This synergistic framework enables the system to adapt its search tools to the evolving complexity of the problem and leverage trajectory-aware, situation-conditioned insights to guide generation. Experiments on several classic combinatorial optimization benchmarks demonstrate that RefineEvo consistently outperforms strong baselines. In particular, RefineEvo delivers superior solution quality while improving token efficiency, enabling more efficient and autonomous heuristic design.
APA
Wu, Y., Pan, J., Zhang, Y., Xu, N., Zeng, F. & Cheng, J.. (2026). RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experience. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:136582-136624 Available from https://proceedings.mlr.press/v306/wu26ap.html.

Related Material