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

arXiv: https://arxiv.org/abs/2609.03338 · HTML: https://mlsanity.com/paper/2609.03338/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 21 of 21)

- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL](https://mlsanity.com/paper/2508.07976/) (2025)
- [SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research](https://mlsanity.com/paper/2308.13149/) (2023)
- [Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles](https://mlsanity.com/paper/2010.14235/) (2020)
- [MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling](https://mlsanity.com/paper/2511.11793/) (2025)
- [SciAgent: Tool-augmented Language Models for Scientific Reasoning](https://mlsanity.com/paper/2402.11451/) (2024)
- [K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization](https://mlsanity.com/paper/2306.05064/) (2023)
- [Deep Research: A Survey of Autonomous Research Agents](https://mlsanity.com/paper/2508.12752/) (2025)
- [Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model](https://mlsanity.com/paper/2510.18855/) (2025)
- [AstroLLaMA: Towards Specialized Foundation Models in Astronomy](https://mlsanity.com/paper/2309.06126/) (2023)
- [Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation](https://mlsanity.com/paper/2606.02684/) (2026)
- [Ai2 Scholar QA: Organized Literature Synthesis with Attribution](https://mlsanity.com/paper/2504.10861/) (2025)
- [Can Large Language Models Unlock Novel Scientific Research Ideas?](https://mlsanity.com/paper/2409.06185/) (2024)
- [KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions](https://mlsanity.com/paper/2403.03866/) (2024)
- [Uni-SMART: Universal Science Multimodal Analysis and Research Transformer](https://mlsanity.com/paper/2403.10301/) (2024)
- [What Should I Cite? A RAG Benchmark for Academic Citation Prediction](https://mlsanity.com/paper/2601.14949/) (2026)
- [DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering](https://mlsanity.com/paper/2601.16478/) (2026)

## Abstract (arXiv)

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.