Austin Bennett(@AustinB31415):Super exciting to see APEX-Agents 1.1 released. From spotting noncommittal answers in the original leaderboard traces to re-designing our tasks and judge model, it’s been amazing to drive this project. At the heart of it was tackling scattergunning – a reward-hacking behavior where models aggressively hedge answers in response to ambiguity. You can learn more about how we tackled it here!

2026.09.08 21:51

Super exciting to see APEX-Agents 1.1 released. From spotting noncommittal answers in the original leaderboard traces to re-designing our tasks and judge model, it’s been amazing to drive this project. At the heart of it was tackling scattergunning – a reward-hacking behavior where models aggressively hedge answers in response to ambiguity. You can learn more about how we tackled it here!