SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesis

2026-09-02

AI Summary

为解决科学文献合成依赖专有服务的问题，SciLENS采用本地化自主代理框架，并通过强化学习和结构可视化方法提高合成效果。

Abstract

Scientific literature synthesis agents increasingly rely on proprietary online services, limiting reproducibility, privacy, and offline deployment. To address this challenge, we introduce SciLENS Scientific Localized Evidence Navigation and Synthesis), a fully local autonomous agent framework operating on a dual-tier infrastructure indexing approximately 12 million academic records. SciLENS pioneers the integration of structural visualization as an actionable tool within the reasoning loop, enabling the agent to compress complex citation topologies into validated data-driven charts and thereby mitigate context exhaustion during macro-level synthesis. To train the agent without human annotation, we develop an automated data synthesis pipeline that extracts multi-hop subgraphs from a citation knowledge graph, verified by cross-model consensus among 20 frontier models. The agent is subsequently aligned through a reverse-decomposition rubric strategy that provides fine-grained process rewards for early planning and strict evidence grounding. Evaluations across six scientific benchmarks encompassing standard QA, citation accuracy, factual reasoning, and structural synthesis demonstrate that SciLENS significantly outperforms open-source baselines and achieves performance comparable to GPT-5.2 and Gemini-3.0-pro. Our source code and data are released at https://github.com/LQgdwind/SciLENS.

Problem

• Scientific Literature Synthesis
• Reproducibility
• Privacy
• Offline Deployment

Innovation

• structural visualization
• autonomous agent
• data synthesis pipeline
• reverse-decomposition rubric