2 papers
cs.CL2026
DIVE: Unlocking Self-Improvement in Frozen Language Models Through Diversity-Driven Skill Evolution
Siheng Xiong, Ali Payani, Oguzhan Gungordu +1
Large language models (LLMs) cannot retain post-deployment experience without parameter updates. We introduce DIVE, a diversity-driven framework that enables frozen LLMs to improve…
cs.NE2026
MOSAIC: Adversarial Co-evolution of Specialist Heuristics and Problem Instances for LLM-based Automated Heuristic Design
Oguzhan Gungordu, Siheng Xiong, Faramarz Fekri
Automated heuristic design (AHD) with large language models (LLMs) has produced strong heuristics for combinatorial optimization problems (COPs). Yet existing frameworks optimize f…