ZJU-REAL

An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.🎨一个开源的 AI...

Build, Evaluate, and Deploy GUI Agents — online RL training, standardized benchmarks, and real-device deployment in one framework.

HugAgentOS: the open-source Agent Harness that runs 24/7

A curated collection of resources, tools, and frameworks for developing GUI Agents.

[EMNLP 2026] Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"

Official code for "Self-Distilled Agentic Reinforcement Learning"

[EMNLP 2026] A Unified Framework for High-Performance and Extensible LLM Steering

[AAAI 2026] GUI-G²: Gaussian Reward Modeling for GUI Grounding

Toward Autonomous Scientific Discovery

[EMNLP 2026 main] Agent-G2 : Gaussian Guidance for Agentic Reinforcement Learning

[ICLR 2026] SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models

SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments

[ECCV 2026] ViewSpatial-Bench:Evaluating Multi-perspective Spatial Localization in Vision-Language Models

Official code for "KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation"

[ACM MM 2025] SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation. https://arxiv.org/abs/2506.03139

A composable framework for reproducible evaluation of long-running agents.

Rubric-Centered Framework for Research-Plan Generation

TTPO: Test-Time Policy Optimization

[AAAI 2026] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency https://arxiv.org/abs/2508.05615

[ICLR 2026] InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models

[NeurIPS 2025] Let LRMs Break Free from Overthinking via Self-Braking Tuning. https://arxiv.org/abs/2505.14604

[ICML 2026] Milestone-Guided Policy Learning for Long-Horizon Language Agents