✳flâneur — a map of the web's best reading

FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale | alphaXiv

alphaxiv.org · 8,595 words · saved by 1 readers

Researchers from UC Berkeley, Stanford, Princeton, MIT, and Bespoke Labs developed FrontierSmith, an automated system that synthesizes open-ended coding problems by mutating existing closed-ended...

Abstract Many real-world coding challenges are open-ended and admit no known optimal solution. Yet, recent progress in LLM coding has focused on well-defined tasks such as feature implementation, bug fixing, and competitive programming. Open-ended coding remains a weak spot for LLMs, largely because open-ended training problems are scarce and expensive to construct. Our goal is to synthesize open-ended coding problems at scale to train stronger LLM coders. We introduce FrontierSmith, an automated system for iteratively evolving open-ended problems from existing closed-ended coding tasks. Start

Explore this link on the map →

related reading