AgenticIR (Agentic Information Retrieval) provides a modular framework where LLM-powered agents autonomously plan and execute IR workflows. It enables the definition of agent roles — such as query generator, document retriever, and summarizer — running in customizable sequences. Agents can fetch raw text, refine queries based on intermediate results, and merge extracted passages into concise summaries. The framework supports multi-step pipelines including iterative web search, API-based data ingestion, and local document parsing. Developers can adjust agent parameters, plug in different LLMs, and fine-tune behavior policies. AgenticIR also offers logging, error handling, and parallel agent execution to accelerate large-scale information gathering. With a minimal code setup, researchers and engineers can prototype and deploy autonomous retrieval systems.

Multi-Agent Inspection Simulation provides a comprehensive framework for simulating and training multiple autonomous agents to perform inspection tasks cooperatively within Unity 3D environments. It integrates with the Unity ML-Agents toolkit, offering configurable scenes with inspection targets, adjustable reward functions, and agent behavior parameters. Researchers can script custom environments, define the number of agents, and set training curricula via Python APIs. The package supports parallel training sessions, TensorBoard logging, and customizable observations including raycasts, camera feeds, and positional data. By adjusting hyperparameters and environment complexity, users can benchmark reinforcement learning algorithms on coverage, efficiency, and coordination metrics. The open-source codebase encourages extension for robotics prototyping, cooperative AI research, and educational demonstrations in multi-agent systems.