Multilingual GSM-Symbolic: What determines capability transfer across languages? Paper • 2610.03367 • Published Oct 2 • 23
Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation Paper • 2609.04298 • Published Sep 9 • 1
The Embedder's Dilemma: LLMs Are Better, but at What Cost? Paper • 2608.12875 • Published Aug 13 • 12
SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work? Paper • 2606.07682 • Published Jun 5 • 2