Updates
1. arXiv updates SWE-Prime: Fewer Trajectories, Better Performance
To improve large language models' ability to resolve real world software issues, prior work has focused on constructing large scale agent trajectory datasets and performing.
Proof: The arXiv Coding-Agent Research page documents the arXiv update.
Impact: Teams evaluating arXiv agent can compare its documented input scope, limits, and deployment fit.
Watch next: Watch access tiers, latency, pricing, benchmark updates.
Canonical host: arxiv.org