OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment
This addresses the problem of scalable and fair novelty assessment for peer reviewers in academic research, though it appears incremental as it builds on existing LLM and retrieval methods.
The authors tackled the challenge of evaluating novelty in peer review by developing OpenNovelty, an LLM-powered agentic system that provides transparent, evidence-based novelty analysis, and deployed it on 500+ ICLR 2026 submissions with preliminary results showing it can identify relevant prior work.
Evaluating novelty is critical yet challenging in peer review, as reviewers must assess submissions against a vast, rapidly evolving literature. This report presents OpenNovelty, an LLM-powered agentic system for transparent, evidence-based novelty analysis. The system operates through four phases: (1) extracting the core task and contribution claims to generate retrieval queries; (2) retrieving relevant prior work based on extracted queries via semantic search engine; (3) constructing a hierarchical taxonomy of core-task-related work and performing contribution-level full-text comparisons against each contribution; and (4) synthesizing all analyses into a structured novelty report with explicit citations and evidence snippets. Unlike naive LLM-based approaches, \textsc{OpenNovelty} grounds all assessments in retrieved real papers, ensuring verifiable judgments. We deploy our system on 500+ ICLR 2026 submissions with all reports publicly available on our website, and preliminary analysis suggests it can identify relevant prior work, including closely related papers that authors may overlook. OpenNovelty aims to empower the research community with a scalable tool that promotes fair, consistent, and evidence-backed peer review.