PORA: Learning When More Reasoning Pays Off for LLM Agents
arXiv:2610.27119v1 Announce Type: new Abstract: LLM agents perform tasks over multiple steps and revise their actions based on feedback. As the total reasoning budget is often limited and must support future steps, the agent must choose...
Read more: https://arxiv.org/abs/2610.27119
Scan with your phone
Scan with your phone