Summary
Agents-K1 (arXiv:2506.10662) is an end-to-end knowledge orchestration pipeline that converts raw scientific documents into agent-native scientific knowledge graphs, addressing a gap in LLM-based research agents that focus on agent orchestration but neglect scientific knowledge orchestration. The system integrates three components: a multimodal parser with a five-module schema capturing entities, multimodal evidence, citations, and typed inter-entity relations across full papers rather than abstracts alone; a 4B information-extraction backbone trained with GRPO under rule-based rewards; and graphanything, a CLI agent interface unifying web search, multimodal graph retrieval, and cross-document traversal. The authors processed 2.46 million scientific papers across six disciplines to build Scholar-KG, releasing a 1-million-paper subset with full access via SCP. The pipeline also extends to general-domain corpora and schema-compliant data synthesis. Experiments show superior performance in scientific information extraction, knowledge graph construction, and multi-hop scientific reasoning.
Paper Overview
Field: Machine Learning
Authors: Zongsheng Cao, Bihao Zhan, Jinxin Shi
Published: 2025-06-13
arXiv: 2506.10662
Abstract
Current LLM-based research agents have advanced through agent orchestration, yet largely overlook scientific knowledge orchestration. Existing works often reduce papers to abstracts, surface mentions, and flat cites edges, omitting key entities, claims, evidence, mechanisms, and method lineages essential for scientific reasoning. To this end, the authors introduce Agents-K1, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs.
Agents-K1 integrates three components under a unifying theoretical foundation:
- Multimodal parser: a five-module schema capturing entities, multimodal evidence, citations, and typed inter-entity relations across the full paper rather than abstracts alone.
- 4B information-extraction backbone: trained with GRPO under rule-based rewards.
- graphanything CLI: a three-source agent interface unifying web search, multimodal graph retrieval, and cross-document traversal.
Building on this, the team processed 2.46 million scientific papers across six disciplines to construct
Scholar-KG, releasing a 1-million-paper subset, with the full Scholar-KG accessible via an SCP link. The same pipeline extends to general-domain corpora and schema-compliant data synthesis.
Extensive experiments demonstrate that Agents-K1 achieves superior performance in scientific information extraction, knowledge graph construction, and multi-hop scientific reasoning.
---
*Auto-collected on 2026-06-14*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/177981278