Release technical blueprints and evaluation benchmarks, establish protocols for intelligent agent collaboration, promote standardization of core AI modules, and advocate for AI ethics and safety standards.
Build an open-source, secure intelligent agent community that enhances human interests and values.
About Awesome things towards foundation agents. Papers / Repos / Blogs / ...
Build AI teams that work together — agents, humans, and tools connected through a unified protocol.
A Python runtime for multi-entity AI collaboration — agents, humans, and tools on a shared protocol layer.
Official Repo of Harnessing Agentic Evolution (https://arxiv.org/abs/2605.13821)
Next paradigm for LLM Agent. Unify plan and action through recursive code generation for adaptive, human-like decision-making.
We introduce Reasoning via Video, a new paradigm that uses maze-solving video generation to probe multimodal reasoning; our VR-Bench shows that fine-tuned video models consistently outperform strong VLMs on long-horizon spatial planning tasks.
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Loading…
Loading…