Complementing OpenEvolve with experience replay to find solution for a problem that's on par with human-expert SOTA (which no code-generation agent has accomplished before).
Jan 12, 2026
Inference-time scaling for multimodal reasoning, improving accuracy and efficiency under tight compute.
Jan 11, 2026
Proposal outlining the background, goals, methodology, and expected impact of my capstone project.
Dec 23, 2025

TL;DR. We present CASCO-Agent, a large-language-model agent framework that utilizes inference-time scaling with lightweight surrogate feedback to automate the configuratons of expensive simulators.
Sep 27, 2024