IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review

TL;DR

IntrAgent is an LLM-based agent designed to automate precise, content-grounded information retrieval from scientific literature, mimicking human reading behaviors through a two-stage process and evaluated on a new benchmark.

Contribution

The paper introduces IntrAgent, a novel LLM agent with a two-stage pipeline for fine-grained literature-based information retrieval, and presents IntraBench, a new benchmark for evaluation.

Findings

IntrAgent outperforms state-of-the-art RAG and research-agent baselines by 13.2% on average.

The two-stage pipeline effectively mimics human reading and reasoning behaviors.

IntraBench provides a rigorous, expert-annotated dataset across five STEM domains.

Abstract

Scientific research relies on accurate information retrieval from literature to support analytical decisions. In this work, we introduce a new task, INformation reTRieval through literAture reVIEW (IntraView), which aims to automate fine-grained information retrieval faithfully grounded in the provided content in response to research-driven queries, and propose IntrAgent, an LLM-based agent that addresses this challenging task. In particular, IntrAgent is designed to mimic human behaviors when reading literature for information retrieval -- identifying relevant sections and then iteratively extracting key details to refine the retrieved information. It follows a two-stage pipeline: a Section Ranking stage that prioritizes relevant literature sections through structural-knowledge-enabled reasoning, and an Iterative Reading stage that continuously extracts details and synthesizes them into concise, contextually grounded answers. To support rigorous evaluation, we introduce IntraBench, a new benchmark consisting of 315 test instances built from expert-authored questions paired with literature spanning five STEM domains. Across seven backbone LLMs, IntrAgent achieves on average 13.2% higher cross-domain accuracy than state-of-the-art RAG and research-agent baselines.