# hkuds/ai-researcher **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/hkuds-ai-researcher).** 4,492 stars · 549 forks · Python ## Links - GitHub: https://github.com/HKUDS/AI-Researcher - Homepage: https://arxiv.org/abs/2505.18705 - awesome-repositories: https://awesome-repositories.com/repository/hkuds-ai-researcher.md ## Topics `ai-researcher` ## Description AI-Researcher is an LLM research automation framework and scientific workflow orchestrator designed to automate the end-to-end discovery process. It employs autonomous AI research agents to identify research gaps, formulate hypotheses, and execute scientific discovery workflows independently. The system integrates an automated literature review tool for gathering and analyzing academic papers and code repositories with an AI-driven manuscript generator that synthesizes research motivations and experimental results into full-length academic papers. The framework covers a modular research pipeline that includes research material collection, algorithm implementation, and performance validation. It utilizes closed-loop iteration to refine algorithm designs and incorporates benchmarking tools to evaluate agent performance based on correctness, completeness, and quality. A web-based research management interface is provided to configure environment variables and trigger the research process workflows. ## Tags ### Artificial Intelligence & ML - [Autonomous Research Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/autonomous-research-frameworks.md) — Orchestrates the full research lifecycle from literature review to manuscript generation using autonomous AI agents. ([source](https://autoresearcher.github.io/)) - [Agentic Workflow Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/agentic-workflow-orchestration.md) — Orchestrates multi-step research pipelines by chaining autonomous AI agents through literature review, hypothesis generation, and manuscript creation. - [End-to-End Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/audio-transcription/end-to-end-pipelines.md) — Orchestrates the full discovery pipeline from literature review through experimentation to manuscript generation. ([source](https://autoresearcher.github.io/docs)) - [Scientific Discovery Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/audio-transcription/end-to-end-pipelines/scientific-discovery-pipelines.md) — Orchestrates the complete scientific discovery pipeline from literature review and idea generation through algorithm design, implementation, validation, and manuscript creation. ([source](https://cdn.jsdelivr.net/gh/hkuds/ai-researcher@main/README.md)) - [Research Automation Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/research-automation-frameworks.md) — Orchestrates autonomous research agents to automate the full scientific discovery pipeline from literature review to manuscript generation. - [Manuscript Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/research-papers/manuscript-generation.md) — Synthesizes research motivations, experimental results, and algorithm designs into complete academic papers. ### Part of an Awesome List - [Autonomous Research Agents](https://awesome-repositories.com/f/awesome-lists/ai/autonomous-research-agents.md) — Deploys LLM-powered agents to independently identify research gaps, formulate hypotheses, and execute experimental workflows. - [Automated Algorithm Implementation](https://awesome-repositories.com/f/awesome-lists/ai/scientific-research-agents/automated-algorithm-implementation.md) — Transforms conceptual research ideas into functional code implementations with automated testing and iterative refinement. ([source](https://cdn.jsdelivr.net/gh/hkuds/ai-researcher@main/README.md)) - [Research Agent Systems](https://awesome-repositories.com/f/awesome-lists/ai/research-agent-systems.md) — End-to-end automation from hypothesis generation to peer review. ### Education & Learning Resources - [Automated Hypothesis Generation](https://awesome-repositories.com/f/education-learning-resources/research-idea-generation/automated-hypothesis-generation.md) — Generates testable predictions based on identified gaps and prior knowledge to guide experimental design. ([source](https://autoresearcher.github.io/docs)) - [Experimental Implementations](https://awesome-repositories.com/f/education-learning-resources/technical-domain-education/technical-academic-domains/algorithmic-design-analysis/algorithms-and-design-patterns/experimental-implementations.md) — Implements research ideas as code and iteratively refines them based on experimental performance metrics. ### Scientific & Mathematical Computing - [Automated Literature Reviewers](https://awesome-repositories.com/f/scientific-mathematical-computing/automated-literature-reviewers.md) — Collects and analyzes academic papers and code repositories to identify research gaps and relevant prior work. - [Literature Collectors](https://awesome-repositories.com/f/scientific-mathematical-computing/automated-literature-reviewers/literature-collectors.md) — Collects and filters research materials from academic databases and code platforms, evaluating papers and datasets for relevance and quality. ([source](https://cdn.jsdelivr.net/gh/hkuds/ai-researcher@main/README.md)) - [Literature Synthesizers](https://awesome-repositories.com/f/scientific-mathematical-computing/automated-literature-reviewers/literature-synthesizers.md) — Collects, filters, and evaluates academic papers and code repositories to identify research gaps and relevant prior work. - [Research Orchestration](https://awesome-repositories.com/f/scientific-mathematical-computing/research-analysis-workflows/research-and-data-analysis-tools/research-orchestration.md) — Manages and executes multi-step scientific discovery pipelines through a web-based interface with configurable environment settings. - [Scientific Discovery Acceleration](https://awesome-repositories.com/f/scientific-mathematical-computing/scientific-discovery-acceleration.md) — Orchestrates the full research lifecycle from literature review to manuscript generation using autonomous AI agents. - [Scientific Workflow Automators](https://awesome-repositories.com/f/scientific-mathematical-computing/scientific-workflow-automators.md) — Coordinates literature collection, algorithm implementation, performance validation, and manuscript creation in a closed-loop process. - [Gap Identifiers](https://awesome-repositories.com/f/scientific-mathematical-computing/automated-literature-reviewers/gap-identifiers.md) — Analyzes existing literature to pinpoint underexplored areas and open questions for new investigations. ([source](https://autoresearcher.github.io/docs)) ### DevOps & Infrastructure - [Modular Pipeline Architectures](https://awesome-repositories.com/f/devops-infrastructure/cicd-pipeline-automation/cicd-pipeline-management/modular-pipeline-architectures.md) — Structures the research process into interchangeable stages for material collection, algorithm implementation, and validation. ### Software Engineering & Architecture - [Closed-Loop Code Iteration](https://awesome-repositories.com/f/software-engineering-architecture/software-architecture-design/iterative-design-reviews/closed-loop-code-iteration.md) — Repeatedly refines algorithm designs and implementations based on automated testing and performance metrics in a feedback loop. ### Testing & Quality Assurance - [Agent Performance Benchmarks](https://awesome-repositories.com/f/testing-quality-assurance/agent-performance-benchmarks.md) — Assesses agent performance on correctness, completeness, and quality using systematic benchmarking tools. - [Algorithmic Refinement Tools](https://awesome-repositories.com/f/testing-quality-assurance/validation-verification/input-validation/algorithmic-validation-tools/algorithmic-refinement-tools.md) — Executes systematic experiments to evaluate algorithm performance, collects metrics, and iteratively optimizes implementations. ([source](https://cdn.jsdelivr.net/gh/hkuds/ai-researcher@main/README.md)) ### User Interface & Experience - [Research Workflow Launchers](https://awesome-repositories.com/f/user-interface-experience/text-editors/graphical-frontends/web-based-debugger-frontends/gradio-interfaces/research-workflow-launchers.md) — Provides a Gradio-based web UI for configuring environment variables and triggering end-to-end research workflows.