aiwaves-cn/agents

★ 5,922PythonAudience · developerComplexity · 3/5LicenseSetup · moderate

Mindmap

mindmap
  root((repo))
    What it does
      Self-improving agents
      Rewrites own prompts
      Symbolic learning
    How it works
      Forward pass task run
      Language gradients
      Backward prompt update
    Multi-agent
      Pipeline of agents
      Coordination learning
    Tech
      Python
      LLM powered
      Apache 2.0

mindmap root((repo)) What it does Self-improving agents Rewrites own prompts Symbolic learning How it works Forward pass task run Language gradients Backward prompt update Multi-agent Pipeline of agents Coordination learning Tech Python LLM powered Apache 2.0

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Build an AI agent that automatically improves its own instructions over multiple task attempts without you rewriting prompts by hand.

USE CASE 2

Set up a multi-agent pipeline where several AI agents coordinate on a task and the whole system learns to collaborate better.

USE CASE 3

Run experiments in agent self-improvement research using the symbolic learning framework from the accompanying arXiv paper.

Tech stack

Pythonpip

Getting it running

Difficulty · moderate Time to first run · 30min

Requires an LLM API key (e.g. OpenAI) to run the agent training loop.

Use freely for any purpose including commercial products, keep the copyright notice and the Apache 2.0 license file.

In plain English

Agents 2.0 is a Python framework for building AI agents that can learn and improve themselves over time. An AI agent here means a program powered by a large language model (an AI text system) that can take a sequence of steps, use tools, and produce outputs in response to a goal. Most agent frameworks treat the AI's instructions and behavior as fixed once deployed. This project tries a different approach: making those components trainable. The core idea is called symbolic learning. The framework borrows concepts from how neural networks are trained, applying them to language-based agents. A typical training run works like this: the agent executes a task (the forward pass), stores what happened at each step, then evaluates how well it did using a language-based scoring method. It then works backward through those steps producing written analyses (called language gradients) describing what went wrong or could improve at each stage. Finally, the agent uses those analyses to rewrite its own prompts and tool usage, updating itself for the next attempt. This process is designed to let an agent get better at a task through repeated attempts without a human rewriting its instructions by hand. The framework also supports multi-agent setups where several agents work together as nodes in a pipeline, and the same learning process can improve how those agents coordinate. Version 2.0, released in mid-2024, added the symbolic learning and evaluation features. Installation is via pip from the GitHub repository. The project is accompanied by a research paper on arXiv (arxiv.org/abs/2406.18532) that describes the method in detail. Documentation is hosted separately at agentsv2.readthedocs.io. The code is released under the Apache 2.0 license.

Copy-paste prompts

Prompt 1

I want to build a self-improving AI agent using Agents 2.0 that gets better at a specific task over repeated attempts. Show me the minimal Python setup and how to define the task and scoring function.

Prompt 2

Explain how symbolic learning in Agents 2.0 works step by step and show me what the language gradients look like after a failed task run.

Prompt 3

How do I set up a multi-agent pipeline in Agents 2.0 where three agents collaborate on a research task and the system improves their coordination through training?

Open on GitHub → Explain another repo

← aiwaves-cn on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.