EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction Paper • 2609.02783 • Published Sep 2 • 62
ParaTempo: Efficient Parallel Reasoning via Temporal Confidence Paper • 2608.16425 • Published Aug 17 • 41
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding Paper • 2602.01785 • Published Feb 2 • 55