AIWaves AgentsOpen‑source adaptive LLM framework for building, training & deploying autonomous language agents.

AIWaves Agents is an open-source adaptive LLM framework for building, training, and deploying autonomous language agents. It was updated to Agents 2.0, which adds support for agent learning and evaluation through symbolic learning, a systematic framework inspired by neural network training. This framework allows for the training of language agents by creating an analogy between agent pipelines and neural network computational graphs. The framework works by first executing an agent and storing its trajectory, including inputs, outputs, prompts, and tool usage. It then evaluates the outcome using a language-based loss function, back-propagates the loss to calculate language gradients, and updates the agent's symbolic components accordingly. This process enables agents to learn and adapt over time. Agents 2.0 also supports the optimization of multi-agent systems by treating nodes as different agents or allowing multiple agents to act within a single node. The framework is designed to be flexible and extensible, supporting various applications and research directions. The project provides an installation guide, including options for installing from the Git repository or for local development. It also includes citations for related research papers. The framework's strengths lie in its innovative approach to agent learning and its potential for advancing research in autonomous language agents. However, its complexity and reliance on carefully designed prompt pipelines may present challenges for users.