Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Framework: Multi-Agent LLMs For Conversational Task-Solving (MALLM)

Human-in-the-loop adversarial workflows for high-stakes research audit: from ChatGPT-Gemini duels to 4-model MAD.

Research-backed methodology for multi-AI collaborative decision-making with structured debate, consensus synthesis, and bias reduction

A brutally fault-tolerant Mixture-of-Agents (MoA) pipeline built in pure Python. Designed to orchestrate chaotic, round-robin LLM proxy endpoints through a rigorous 4-stage Agentic Workflow (Generate ➔ Cross-Critique ➔ Rebuttal ➔ Judge). Built to eradicate hallucination and guarantee absolute accuracy in complex, multi-step reasoning tasks.

Enable autonomous AI agents to optimize LLM training code through iterative experiments and improve models without manual intervention overnight

Automate code improvement by detecting issues, fixing bugs, and simplifying code on separate branches before merging to main.

Generate research papers autonomously by chatting with OpenClaw, using Python 3.11+, with a self-evolving framework and extensive test coverage.

Build autonomous ML research in Elixir: design, train, and iterate GPT models across GPUs with fault-tolerant BEAM concurrency

AI Agent Workspace Redesign: A structured multi-agent debate methodology for managing AI agent workspaces (memory, file organization, protection tiers, boot sequences)

Research paper on how agentic debate pipelines can be constructed to reduce hallucinations in LLMs with open-source and commercial models

Neurips paper code - Evaluating and enhancing Large Language Models (LLMs) using mathematical datasets through innovative Multi-Agent Debate Architecture, without traditional fine-tuning or Retrieval-Augmented Generation techniques. This project explores advanced strategies to boost LLM capabilities in mathematical reasoning.

supporting codes for the study on multi-agent debate protocols