An environement builder for hierarchical reasoning research
Code for ICRA-25 "Bootstrapping Object-level Planning with LLMs"
SAGE: Self-Adaptive Goal-directed Executor — A multi-tool LLM agent with DAG-based hierarchical planning, ReAct reasoning, and evidence-guided self-correction for automated research synthesis. Built from scratch, no frameworks.
Universal autonomous agent framework with ReAct loop, multi-provider LLM routing, reasoning graph, and MCP integration, domain-agnostic for building specialized AI agents.
In this repo there are two versions of Multiscale AI design as originally ideated by Weber. A version with and without hierarchical planning is added as they were part of a research, link to come.
Add a description, image, and links to the hierarchical-planning topic page so that developers can more easily learn about it.
To associate your repository with the hierarchical-planning topic, visit your repo's landing page and select "manage topics."