arXiv:2609.36303v1 Announce Type: cross
Abstract: Recent advances in agentic heuristic design use AI agents and execution feedback to automate algorithm discovery for challenging optimization problem...
By Feijie Wu, Hugo Barbalho, Konstantina Mellou, Marco Molinaro, Jing Gao, Ishai Menache, Xinzhi Zhang, Sirui Li
The paper introduces Discovery Loop, a lightweight system that employs a large language model (LLM) to iteratively evolve optimization algorithms for the Packomania circle‑packing benchmark. Starting from a simple seed solver, the LLM proposes algorithmic improvements guided by a scoreboard and a history of prior ideas, evaluates each candidate against an independent verifier, and retains only successful changes. Within 15 iterations and a total LLM cost of $27.72, the system broke 10 Packomania records for N between 101 and 114, improving the best known solutions by 2.4%–5.4%.
The work demonstrates that a cost‑efficient, LLM‑driven approach can rapidly advance state‑of‑the‑art solutions in a complex optimization domain, suggesting broader potential for democratizing automated scientific discovery.
By Wes Sander
arXiv:2609.25510v1 Announce Type: new
Abstract: Large language models (LLMs) can improve solutions to verifiable scientific and algorithmic problems by spending additional computation at test time. R...
By Jacob Beck, Philip V. Ogren, Ari Kobren
arXiv:2606. 08904v1 Announce Type: new Abstract: Macro placement is a fundamental step in modern chip physical design, playing a crucial role in determining the solution quality of high-dimensional combinatorial optimization problems.
By Shibing Mo, Jing Liu, Jianchu Xu, Ruilin Wu
arXiv:2606. 29082v1 Announce Type: cross Abstract: Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture?
By Young-Jun Lee, Seungone Kim, Minki Kang, Alistair Cheong Liang Chuen, Zerui Chen, Seungho Han, Taehee Jung, Dongyeop Kang
arXiv:2605. 29649v2 Announce Type: replace Abstract: Heuristic search is the dominant paradigm in symbolic AI planning, and the strongest heuristics are the result of decades of work by planning researchers.
By Elliot Gestrin, Jendrik Seipp