REVIEW 1 cited by
ReZero: Enhancing LLM search ability by trying one-more-time
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Retrieval-Augmented Generation (RAG) improves Large Language Model (LLM) performance on knowledge-intensive tasks but depends heavily on initial search query quality. Current methods, often using Reinforcement Learning (RL), typically focus on query formulation or reasoning over results, without explicitly encouraging persistence after a failed search. We introduce ReZero (Retry-Zero), a novel RL framework that directly rewards the act of retrying a search query following an initial unsuccessful attempt. This incentivizes the LLM to explore alternative queries rather than prematurely halting. ReZero demonstrates significant improvement, achieving 46.88% accuracy compared to a 25% baseline. By rewarding persistence, ReZero enhances LLM robustness in complex information-seeking scenarios where initial queries may prove insufficient.
Forward citations
Cited by 1 Pith paper
-
Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
A GRPO-based method that rewards only self-reflection tokens, not answer tokens, improves LLM accuracy on function calling and Countdown math tasks using only binary success/failure feedback.
Discussion (0). Continue with ORCID to comment.