Helix is presented, the first framework for LLM-driven algorithmic evolution of placement algorithms within a production C++ (RTL-to-GDS) flow and achieves 7 × larger fitness gains against a comparable-budget LLM single-shot baseline.
Discovery Loop is a lightweight system that uses a large language model (LLM) to iteratively evolve optimization algorithms to improve the best known solutions for 10 values of N in the range 101-114, with gains of 2.4%-5.4% over prior records.
LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prior work typically optimizes performance gain over a fixed number of iterations. We argue that practical optimization should maximize gain per...
SEDIMA is introduced, a persistent hierarchical insight memory for evolutionary search agents that distills raw traces into natural-language insights, clusters them by semantic similarity using attention-weighted centroids, and retrieves relevant guidance to condition future mutations, accumulating transferable knowled...
Amirhossein Abaskohi, Mahdi Mostajabdaveh, Zi-Rui Zhou· Proceedings of the Second Wo...· 0 citations
This work presents PlaceReasoner-Beta, a verifier-guided multi-agent framework that reformulates macro placement as a closed-loop reasoning problem rather than black-box optimization, demonstrating that reasoning over spatial structure under physical-design feedback can improve end-to-end layout quality beyond proxy-ob...
Qiufeng Li, Cheng-Xuan Wang, Rong-Qian Chen et al.· 0 citations
This work extends Compute-Aligned Training to this setting through an abstraction of policy-guided search, deriving tractable, trace-supported losses and introduces a search-agnostic uniform-allocation (UA) loss that accounts for the budget without specifying the specific search.
LLM-guided evolutionary search can discover complex programs, but existing methods mostly only save candidate programs and fitness scores while discarding which component edits produced which fitness metric changes. Existing methods force the mutator LLM to infer the effect of prior edits from cluttered histories, maki...
Ethan Lin, Jinming Nian, Yi Fang· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.