This repository implements emergent communication in multi-agent reinforcement learning using PyTorch. Users can configure sender and receiver neural networks to play referential games or cooperative navigation, encouraging agents to develop a discrete or continuous communication channel. It offers scripts for training, evaluation, and visualization of learned protocols, along with utilities for environment creation, message encoding, and decoding. Researchers can extend it with custom tasks, modify network architectures, and analyze protocol efficiency, fostering rapid experimentation in emergent agent communication.

Deep Research AI Agent is an open-source Python framework designed for conducting comprehensive research tasks. It leverages integrated web search, PDF ingestion, and NLP pipelines to discover relevant sources, parse technical documents, and extract structured insights. The agent chains requests through LangChain and OpenAI, enabling context-aware question answering, automated citation formatting, and multi-document summarization. Researchers can adjust search scopes, filter by publication date or domain, and output reports in markdown or JSON. This tool minimizes manual literature review time and ensures consistent, high-quality summaries across diverse research domains.