# Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

arXiv: https://arxiv.org/abs/2512.16969 · HTML: https://mlsanity.com/paper/2512.16969/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2025.

## Built on by (most cited first, 28 of 28)

- [InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing](https://mlsanity.com/paper/2603.09877/) (2026)
- [InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery](https://mlsanity.com/paper/2602.08990/) (2026)
- [ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research](https://mlsanity.com/paper/2606.07591/) (2026)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges](https://mlsanity.com/paper/2603.11863/) (2026)
- [DeepInnovator: Triggering the Innovative Capabilities of LLMs](https://mlsanity.com/paper/2602.18920/) (2026)
- [SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems](https://mlsanity.com/paper/2605.10246/) (2026)
- [SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discovery](https://mlsanity.com/paper/2602.09132/) (2026)
- [HarmonyCell: Automating Single-Cell Perturbation Modeling under Semantic and Distribution Shifts](https://mlsanity.com/paper/2603.01396/) (2026)
- [Evaluating the Progression of Large Language Model Capabilities for Small-Molecule Drug Design](https://mlsanity.com/paper/2604.16279/) (2026)
- [StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction](https://mlsanity.com/paper/2605.06642/) (2026)
- [Intern-S2-Preview: Scientific Agentic Foundation Model](https://mlsanity.com/paper/2608.13505/) (2026)
- [SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence](https://mlsanity.com/paper/2512.22334/) (2025)
- [FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration](https://mlsanity.com/paper/2603.29557/) (2026)
- [SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification](https://mlsanity.com/paper/2606.04579/) (2026)
- [AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities](https://mlsanity.com/paper/2607.13705/) (2026)
- [Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale](https://mlsanity.com/paper/2601.01330/) (2026)
- [Learning Domain Knowledge in Multimodal Large Language Models through Reinforcement Fine-Tuning](https://mlsanity.com/paper/2601.16419/) (2026)
- [Embodied Science: Closing the Discovery Loop with Agentic Embodied AI](https://mlsanity.com/paper/2603.19782/) (2026)
- [BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMs](https://mlsanity.com/paper/2605.30900/) (2026)
- [TruthInsightBench: An Evidence-Grounded Benchmark for Automated Evaluation of Open-Ended Scientific Discovery Agents](https://mlsanity.com/paper/2609.05079/) (2026)
- [MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation](https://mlsanity.com/paper/2610.11966/) (2026)
- [Can Large Language Models Simulate Human Cognition Beyond Behavioral Imitation?](https://mlsanity.com/paper/2603.27694/) (2026)
- [AblateCell: A Reproduce-then-Ablate Agent for Virtual Cell Repositories](https://mlsanity.com/paper/2604.19606/) (2026)
- [ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning](https://mlsanity.com/paper/2605.18799/) (2026)
- [SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks](https://mlsanity.com/paper/2606.15872/) (2026)
- [Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation](https://mlsanity.com/paper/2607.08758/) (2026)
- [Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations](https://mlsanity.com/paper/2608.00711/) (2026)

## Abstract (arXiv)

Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning. SGI-Bench comprises over 1,000 expert-curated, cross-disciplinary samples inspired by Science's 125 Big Questions, enabling systematic evaluation of state-of-the-art LLMs. Results reveal gaps: low exact match (10--20%) in deep research despite step-level alignment; ideas lacking feasibility and detail; high code executability but low execution result accuracy in dry experiments; low sequence fidelity in wet protocols; and persistent multimodal comparative-reasoning challenges. We further introduce Test-Time Reinforcement Learning (TTRL), which optimizes retrieval-augmented novelty rewards at inference, enhancing hypothesis novelty without reference answer. Together, our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery.