Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks
Authors:
- Weiwen XuWXWeiwen Xu
- Ruochen ZhaoRZRuochen Zhao
- Fangkai JiaoFJFangkai Jiao
- Shafiq JotySJShafiq Joty
- Lidong BingLBLidong Bing
Top Cited Papers
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 25589-25604
Abstract
Xingxuan Li, Weiwen Xu, Ruochen Zhao, Fangkai Jiao, Shafiq Joty, Lidong Bing. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI2024
- Open-RAG: Enhanced Retrieval Augmented Reasoning with Open-Source Large Language Models2024
- REPLUG: Retrieval-Augmented Black-Box Language Models2024
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society2023
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models2023
- Reflexion: language agents with verbal reinforcement learning2023
- Measuring and Narrowing the Compositionality Gap in Language Models2023
- Training Language Models to Follow Instructions with Human Feedback2022
- Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems2017
- Learning to rank using gradient descent2005