ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent.
Renat AksitovSobhan MiryoosefiZonglin LiDaliang LiSheila BabayanKavya KopparapuZachary FisherRuiqi GuoSushant PrakashPranesh SrinivasanManzil ZaheerFelix X. YuSanjiv KumarPublished in: CoRR (2023)
Keyphrases
- multi step
- reasoning process
- resource bounded
- reasoning engine
- lower bounding
- multi agent
- single step
- external events
- multi agent systems
- autonomous agents
- current situation
- reasoning mechanism
- multiagent systems
- cognitive agents
- intelligent agents
- knn
- multiple agents
- bdi agents
- mobile agents
- k nearest neighbor
- practical reasoning
- plan execution
- tumor classification
- data sets
- past experience
- agent model
- knowledge base
- supervised learning