multi-step-actions

Tag

#multi-step-actions

Co-Evolving Acting and Forecasting for Language Agents

Hugging Face Daily Papers ↗ · 2026-10-15 Cached

CoPE 论文提出通过在成功轨迹上训练多步动作目标，使语言智能体的行动与预测能力协同演化，从而在不增加推理开销的情况下提升样本效率，相比 GRPO 与 ECHO 在多项基准上取得更强表现。

0 favorites 0 likes