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

Code for "Multiple LLM Agents Debate for Equitable Cultural Alignment" [ACL 2025 Oral]

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.

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

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

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

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.

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

supporting codes for the study on multi-agent debate protocols

Organize genealogy research with structured AI prompts, vault templates, and workflows for source-backed family history work

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