Test-time Corpus Feedback: From Retrieval to RAG

TL;DR

This paper discusses the evolution of Retrieval-Augmented Generation (RAG) systems towards incorporating iterative feedback mechanisms, transforming retrieval from a static step into a dynamic, learnable process to enhance complex NLP tasks.

Contribution

It provides a structured overview of feedback-driven retrieval and ranking methods, bridging IR and NLP to improve RAG system performance.

Findings

Feedback mechanisms improve retrieval accuracy.

Dynamic retrieval enhances reasoning in complex tasks.

Bridging IR and NLP perspectives advances RAG systems.

Abstract

Retrieval-Augmented Generation (RAG) has emerged as a standard framework for knowledge-intensive NLP tasks, combining large language models (LLMs) with document retrieval from external corpora. Despite its widespread use, most RAG pipelines continue to treat retrieval and reasoning as isolated components, retrieving documents once and then generating answers without further interaction. This static design often limits performance on complex tasks that require iterative evidence gathering or high-precision retrieval. Recent work in both the information retrieval (IR) and NLP communities has begun to close this gap by introducing adaptive retrieval and ranking methods that incorporate feedback. In this survey, we present a structured overview of advanced retrieval and ranking mechanisms that integrate such feedback. We categorize feedback signals based on their source and role in improving the query, retrieved context, or document pool. By consolidating these developments, we aim to bridge IR and NLP perspectives and highlight retrieval as a dynamic, learnable component of end-to-end RAG systems.