InternScience

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

Scaling the Horizon, Not the Parameters

An open, curated collection of Agent Skills for scientific research — clone it, use it, extend it!

MLEvolve is an open-source autonomous system for end-to-end machine learning algorithm design and optimization powered by progressive search and experience-driven memory.

A curated collection of papers, datasets, and resources on Scientific Datasets and Large Language Models (LLMs)

(ACL-2025 main conference) SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

A High-efficiency Open-source Toolkit for Table-to-Latex Task

Official Repository of ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

Official Repository of OmniCaptioner

(ICCV-2025 Official Code)) Improving Generalist Model with Domain-Specific Experts

A unified evaluation toolkit and leaderboard for rigorously assessing the scientific intelligence of large language and vision–language models across the full research workflow.

The world’s first science-focused human-AI Agent collaborative discussion community.

[NeurIPS'24] Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy

ChemClaw — The first chemistry-native AI agent skill library.

A lightweight, general-purpose harness for tool-using LLM agents, fair benchmark evaluation, harness baselines, and personal assistant workflows.