Official Repository of Absolute Zero Reasoner

🤗 smolagents: a barebones library for agents that think in code.

Evolve your language agent with Agentic Context Engineering (ACE)

verl: Volcano Engine Reinforcement Learning for LLMs

Latent Collaboration in Multi-Agent Systems

RL research on Android devices.

Open source code for Paper: Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions

Hash function quality and speed tests

Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping" by Zhiheng Xi et al.

The official implementation of the paper "Mem-α: Learning Memory Construction via Reinforcement Learning"

程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

A beautiful, simple, clean, and responsive Jekyll theme for academics

AlphaGo Moment for Model Architecture Discovery.

Rust version of THU uCore OS. Linux compatible.

Semantic Image Synthesis with SPADE

Generative AI Act II: Test Time Scaling Drives Cognition Engineering

Compacts the size of the ever-growing WSL vhdx images.