notesum.ai

Published at October 22

cs.CL

cs.AI

Released Date: October 22, 2024

Authors: Chen Yang¹, Chenyang Zhao¹, Quanquan Gu¹, Dongruo Zhou¹

Aff.: ¹Institution Not Specified

Algorithm	Performance
Algorithm	Llama3.1 8b	Llama3.1 70b
Reflexion ²²2The original codebase of Reflexion struggles to perform on most tasks with the smaller Llama3.1 8b model. This is primarily because the model tends to repeat the same action, leading to task failure. To mitigate this, we introduced a resampling mechanism to enhance Reflexion performance, which activates when the model begins to repeat actions. This modification significantly improved Reflexion’s performance.	86	94
RAP	70	93
CoPS	94	100