AI Paper Atlas

Research map / Large language models / AI and society

SciNet: Evaluating AI Agents in Relation-Aware Scientific Literature Retrieval

Chenyang Shao, Fengli Xu, Yong Li

ICML 2026 · Large language models › AI and society · approach: Social-science view of AI evaluation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use deep research agent o3-deep-research instead of SciBERTretrieval model · SciNet ego-centric noveltyNovelty-Recall@50: 0.00% -> 1.47%Improved
use deep research agent o4-mini-deep-research instead of SciBERTretrieval model · SciNet ego-centric disruptionDisruption-Recall@50: 0.00% -> 4.71%Improved
use gpt-4o-search instead of Qwen3-Embedretrieval model · SciNet pair-wiseCite-Acc: 11.34% -> 48.65%Improved
use o3-deep-research instead of gpt-4o-searchretrieval model · SciNet pair-wiseCoMention-Acc: 69.94% -> 75.68%Improved
use o3-deep-research instead of gpt-4o-searchretrieval model · SciNet pair-wiseCoMention-Paragraph: 7.50% -> 17.09%Improved
use PaperQA instead of Qwen3-Embedretrieval model · SciNet pair-wiseCite-Acc: 11.34% -> 8.43%Hurt
use gpt-4o-search instead of o3-deep-researchretrieval model · SciNet path-wiseConsistency: 63.28% -> 65.52%Improved
use o3-deep-research instead of gpt-4o-searchretrieval model · SciNet path-wiseConnectivity: 10.30% -> 14.54%Improved
use o3-deep-research instead of SciBERTretrieval model · SciNet path-wiseRationality-Human: 1.72 -> 7.06Improved
use gpt-4o-mini-search instead of gpt-4o-searchretrieval model · SciNet ego-centric noveltyNovelty-SoS: 6.440 -> 6.363Hurt
use Deep Research System instead of Base LLM for literature reviewsurvey generator · Literature review human ranking (40 queries)average rank: 3.00 -> 2.20Improved
use Search-enabled LLM instead of Base LLM for literature reviewsurvey generator · Literature review human ranking (40 queries)average rank: 3.00 -> 3.58Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy