看看闭源模型暗地里怎么想问题的——它们也会纠结和自我怀疑，而长度惩罚可能就是解药。
一条推文揭示了闭源推理模型（如Claude、GPT系列）的原始推理轨迹，这些轨迹通常对用户隐藏。数据表明模型会像人类一样过度思考。Dustin Tran指出，通过更好的长度惩罚（length penalty）可以减少这种过度思考，而无需新的奖励函数。讨论涉及并行与顺序工具调用、工具与基座模型能力边界、单智能体与子智能体等策略。
The raw reasoning traces of these models is pretty funny. Most people don’t see them since they’re h...
The raw reasoning traces of these models is pretty funny. Most people don’t see them since they’re hidden on the closed models. They constantly overthink, kind of like us in our minds. Dustin Tran @dustinvtran Believe in the length penalty. Parallel vs sequential tools, tool vs base model capability, single agent vs subagents, thinking strategy, truncation, doomlooping, exploration. You don't need new rewards, you need a better length penalty. 🔗 View Quoted Tweet 💬 3 🔄 0 ❤️ 11 👀 3653 📊 3 ⚡