Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23

A Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and Prospects

[EMNLP '23] Discriminator-Guided Chain-of-Thought Reasoning

Autonomous agent networks for task automation that requires multi-step reasoning

[ICCV 2025] A Benchmark for Multi-Step Reasoning in Long Narrative Videos

[ACL 2023] Learning Multi-step Reasoning by Solving Arithmetic Tasks. https://arxiv.org/abs/2306.01707

TreeThinkerAgent is a lightweight orchestration layer that turns any LLM into an autonomous multi-step reasoning agent. It supports multi-step planning, tool execution, and final synthesis while exposing the entire reasoning process as a tree you can explore.

OpenDsStar is an open-source implementation of the DS-Star agent that replaces file-based workflows with a flexible, tool-centric architecture. It supports incremental execution, reuses intermediate results, and makes complex multi-step agents more modular, efficient, and extensible.

From Symbolic Logic Reasoning to Soft Reasoning: A Neural-Symbolic Paradigm

Official repository for ODQA experiments from Decomposed Prompting: A Modular Approach for Solving Complex Tasks, ICLR23

Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation

Official implementation for "Get an A in Math: Progressive Rectification Prompting" (AAAI 2024)

PARARULE Plus: A Larger Deep Multi-Step Reasoning Dataset over Natural Language

Implementation of "Building Agentic RAG with LlamaIndex" offered by DeepLearning.AI focusing on developing intelligent research agents using the Retrieval-Augmented Generation (RAG) framework.

Sequential thinking for AI agents: a reusable skill and CLI runtime for stepwise reasoning, revision, replay, and convergence — no extra MCP server required.

VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models

The course teaches how to fine-tune LLMs using Group Relative Policy Optimization (GRPO)—a reinforcement learning method that improves model reasoning with minimal data. Learn RFT concepts, reward design, LLM-as-a-judge evaluation, and deploy jobs on the Predibase platform.

MCP-based OSINT intelligence platform with LangGraph AI agent. Implements multi-step reasoning (task decomposition, hypothesis testing, self-reflection, verification) for autonomous geopolitical research. Supports Gemini, Grok, Ollama, and Docker Model Runner

AI-powered research agent that crawls the internet, reports in markdown, without losing control

A general-purpose X-Ray library and dashboard that provides visibility into multi-step decision pipelines by capturing and visualizing why each decision was made.