Zihan "Zenus" Wang(@wzenus):🧵 Claude-Opus-4.8 takes you too much tokens - but is this issue general across agents? Do agents know how much they'll spend? Introducing Budget-Aware Agents (BAGEN): We study budget awareness across 4 envs & 5 frontier agents, and find structured failures in most of them. 👇

Zihan "Zenus" Wang

@wzenus

Reasoning agent / RL / efficiency research @NorthwesternU & @nvidia. Ex @deepseek_ai @Microsoft @yutori_ai @uiuc_nlp @RUC1937.

参加 March 2022

722 フォロー中 23K ファン

Zihan "Zenus" Wang@wzenus

2026.05.29 16:27

🧵 Claude-Opus-4.8 takes you too much tokens - but is this issue general across agents? Do agents know how much they'll spend? Introducing Budget-Aware Agents (BAGEN): We study budget awareness across 4 envs & 5 frontier agents, and find structured failures in most of them. 👇