1
Humans Still Beat AI in the Long Horizon
人类在长期规划任务中依然优于AI，概率公式揭示优化难度随目标值非线性增长，值得关注。
Article URL: https://joyemang33.github.io/blog/2026/humans-dont-just-sample/ Comments URL: https://news.ycombinator.com/item?id=48564319 Points: 2 # C…
2
WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning
在《我的世界》中实现长期规划，一项名为WISE的智能体通过“原因-选择”推理突破复杂任务，为AI自主决策提供新范式。
arXiv:2606.12852v1 Announce Type: new Abstract: Rapid advances have been made in developing general-purpose embodied agent in environments like Minecr…
3
Prompt reinforcing for long-term planning of large language models
新方法Prompt Reinforcing提升大模型长期规划能力，精准解决复杂任务。
arXiv:2510.05921v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved remarkable success in a wide range of natural lan…