Search papers, labs, and topics across Lattice.
SciLENS is an innovative framework for autonomous scientific literature synthesis that operates locally, addressing issues of reproducibility and privacy by indexing around 12 million academic records. By integrating structural visualization into its reasoning process, SciLENS effectively compresses complex citation networks into actionable charts, which helps mitigate context exhaustion during synthesis tasks. Evaluations reveal that SciLENS not only surpasses open-source baselines but also achieves performance levels comparable to leading models like GPT-5.2 and Gemini-3.0-pro.
SciLENS outperforms existing models in scientific literature synthesis by leveraging structural visualization to enhance reasoning and context retention.
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.
