RubricCraft: Where Solutions Diverge, Criteria Emerge

• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.

• articleInducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent EvaluationDarragh Quinn, David Dylan, Roisin Healy, Fionn Carroll, Maeve Donnelly, Cormac Sheehan
• articleCriticGen: Generation-Aware Evaluation as Actionable FeedbackHuifang Du, Zecheng Zuo, Sen Wang, Chenghao Fan, Haofen Wang, Yehui Yang
• articleSWE-Duel: Towards a Self-Scaling Arena for Coding AgentsWei Minn, Zhensu Sun, Lwin Khin Shar, David Lo

Checking sign-in…

Loading comments…