CLI-Anything: Making ALL Software Agent-Native

OpenClaw-RL: Train any agent simply by talking

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervision, and formulate scientific taste learning as a preference…

Scaling Deep Research via Reinforcement Learning in Real-world Environments.

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.

[ACM CSUR 2025] Understanding World or Predicting Future? A Comprehensive Survey of World Models

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

The Open Source Code for LLM4SD (Large Language Models for Scientific Synthesis, Inference and Explanation)

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

MOVA: Towards Scalable and Synchronized Video–Audio Generation

This is the repo of Data Darwinism

Self-Adapting Language Models

Official JAX implementation of End-to-End Test-Time Training for Long Context

LLM-in-Sandbox: From Coding Agent to General Agent

[CVPR 2026] ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding（书生 · 妙析多模态美学理解大模型）

EvoCUA: Evolving Computer Use Agent

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

[EMNLP2025] From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery