AutoAct

[ACL 2024] AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning

open-sourceagent-frameworks
237
Stars
+8
Stars/month
0
Releases (6m)

Star Growth

+1 (0.4%)
231237242Mar 27Apr 1

Overview

AutoAct is an automatic agent learning framework designed for question answering tasks that eliminates the dependency on expensive closed-source models like GPT-4 and large-scale annotated datasets. Published at ACL 2024, the framework introduces a novel approach to creating language agents from scratch through self-planning mechanisms. AutoAct automatically synthesizes planning trajectories without human assistance or guidance from proprietary models, making it accessible for researchers and developers with limited resources. The system employs a division-of-labor strategy that intelligently differentiates tasks based on target information and synthesized trajectories, creating specialized sub-agent groups to handle complex problems collaboratively. This approach allows the framework to achieve competitive performance compared to existing baselines while maintaining cost-effectiveness and reproducibility. The framework supports various open-source language models and provides a comprehensive solution for organizations looking to build capable agent systems without relying on expensive commercial APIs or extensive manual data annotation efforts.

Deep Analysis

Key Differentiator

vs ReAct/Reflexion/BOLAA: division-of-labor strategy automatically creates specialized Plan/Tool/Reflect sub-agents from self-synthesized trajectories — zero dependency on closed-source model data or human annotations

Capabilities

  • Automatic agent learning without large-scale annotated data
  • Self-synthesized planning trajectory generation
  • Division-of-labor with specialized sub-agents (Plan, Tool, Reflect)
  • Tool library integration with automatic selection
  • LoRA fine-tuning for agent specialization
  • Multi-hop QA task solving (HotpotQA, ScienceQA)

🔗 Integrations

Bing Search APILangChainFastChatDeepSpeedHuggingFace

Best For

  • Research on automatic agent learning without GPT-4 dependency
  • Multi-hop QA requiring complex question decomposition
  • Teams wanting to train specialized sub-agents from self-generated data

Not Ideal For

  • Production real-time applications
  • Tasks without clear tool libraries
  • Teams unable to afford Bing API costs or GPU resources

Languages

Python

Deployment

local GPU clusterdistributed training (8 GPUs via DeepSpeed)

Known Limitations

  • Requires Bing Search API key (paid)
  • Trajectory filtering needed for quality (reward ≥ 1)
  • Context length limited to 4096 tokens
  • Dependent on tool library quality for performance

Pros

  • + Eliminates dependency on expensive closed-source models like GPT-4, making agent development more accessible and cost-effective
  • + Automatically synthesizes planning trajectories without requiring human annotation or manual trajectory creation
  • + Implements division-of-labor strategy with specialized sub-agents for improved task decomposition and completion

Cons

  • - Primarily focused on question answering tasks, which may limit applicability to other agent use cases
  • - Requires an existing tool library to function effectively, adding setup complexity
  • - Performance may vary significantly depending on the quality and capabilities of the underlying open-source language model used

Use Cases

  • Building cost-effective QA agents for organizations without access to expensive closed-source language models
  • Creating reproducible agent systems in research environments with limited annotated training data
  • Developing multi-agent systems that require automatic task decomposition and specialized sub-agent coordination

Getting Started

1. Clone the repository from GitHub using 'git clone https://github.com/zjunlp/AutoAct' 2. Install dependencies by running 'pip install -r requirements.txt' in the project directory 3. Set up your tool library and configure the framework to begin automatic trajectory synthesis and agent training

Compare AutoAct