AI Self-Planning Beats Fixed Algorithms
New framework lets LLMs plan their own search paths, outperforming traditional fixed algorithms in code and math tasks with lower cost.
ImportanceMaterialEvidenceE2 unreplicatedWrite-upQuick
The AgentDiscover framework demonstrates that letting large language models (LLMs) plan their own search paths is more efficient than using fixed algorithms designed by humans.
Traditional AI research assistants typically act only as "proposers," while the search steps are controlled by human-designed algorithms like Monte Carlo tree search. As model capabilities grow, these manual constraints become bottlenecks. AgentDiscover promotes the model to a "planner," using its context as working memory to run experiments and record every attempt in a database. This database serves as long-term memory, allowing the model to freely use, combine, or replace the selection rules of classical algorithms.
Author-reported tests show the framework achieves higher scores at lower cost. In simulations of seven past AtCoder heuristic programming contests, its generated programs would have placed first among human competitors. On eleven mathematical and systems optimization tasks, it matched or exceeded baselines using the same underlying model.
This is an arXiv preprint (submitted October 4, 2026). Results are self-evaluated by the author team and have not yet been independently reproduced.