2023 ReSTMeetsReActSelfImprovementfo

From GM-RKB
(Redirected from Aksitov et al., 2023)
Jump to navigation Jump to search

Subject Headings:

Notes

Cited By

Quotes

Abstract

Answering complex natural language questions often necessitates multi-step reasoning and integrating external information. Several systems have combined knowledge retrieval with a large language model (LLM) to answer such questions. These systems, however, suffer from various failure cases, and we cannot directly train them end-to-end to fix such failures, as interaction with external knowledge is non-differentiable. To address these deficiencies, we define a ReAct-style LLM agent with the ability to reason and act upon external knowledge. We further refine the agent through a ReST-like method that iteratively trains on previous trajectories, employing growing-batch reinforcement learning with AI feedback for continuous self-improvement and self-distillation. Starting from a prompted large model and after just two iterations of the algorithm, we can produce a fine-tuned small model that achieves comparable performance on challenging compositional question-answering benchmarks with two orders of magnitude fewer parameters.

References

;

 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2023 ReSTMeetsReActSelfImprovementfoSanjiv Kumar
Sushant Prakash
Renat Aksitov
Sobhan Miryoosefi
Zonglin Li
Daliang Li
Sheila Babayan
Kavya Kopparapu
Zachary Fisher
Ruiqi Guo
Pranesh Srinivasan
Manzil Zaheer
Felix Yu
ReST Meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent10.48550/arXiv.2312.100032023