Search Results for "multi-objective optimization"

Agent Reinforcement Trainer, or ART is an open-source reinforcement learning framework tailored to training large language model agents through experience, making them more reliable and performant on multi-turn, multi-step tasks. Instead of just manually crafting prompts or relying on supervised fine-tuning, ART uses techniques like Group Relative Policy Optimization (GRPO) to let agents learn from environmental feedback and reward signals. The framework is designed to integrate easily with Python applications, abstracting much of the RL infrastructure so developers can train agents without deep RL expertise or heavy infrastructure overhead. ...

Vibe-Trading is an AI-powered multi-agent financial workspace that converts natural language inputs into executable trading strategies and market analysis. It allows users to describe investment ideas in plain language, which are then translated into code, backtested, and evaluated across global markets. The platform integrates multiple data sources, including equities, crypto, and derivatives, with automatic fallback mechanisms.

CUDA Agent is a research-driven agentic reinforcement learning system designed to automatically generate and optimize high-performance CUDA kernels for GPU workloads. The project addresses the long-standing challenge that efficient CUDA programming typically requires deep hardware expertise by training an autonomous coding agent capable of iterative improvement through execution feedback. Its architecture combines large-scale data synthesis, a skill-augmented CUDA development environment,...

Agent Lightning is an open-source framework developed by Microsoft to train and optimize AI agents using techniques like reinforcement learning (RL), supervised fine-tuning, and automatic prompt optimization, with minimal or zero changes to existing agent code. It’s designed to be compatible with a wide range of agent architectures and frameworks — from LangChain and OpenAI Agent SDKs to AutoGen and custom Python agents — making it broadly applicable across different agent tooling...

Phidata is an open source platform for building, deploying, and monitoring AI agents. It enables users to create domain-specific agents with memory, knowledge, and external tools, enhancing AI capabilities for various tasks. The platform supports a range of large language models and integrates seamlessly with different databases, vector stores, and APIs. Phidata offers pre-configured templates to accelerate development and deployment, allowing users to quickly go from building agents to...

BISHENG is an open LLM application DevOps platform, focusing on enterprise scenarios. It has been used by a large number of industry-leading organizations and Fortune 500 companies. "Bi Sheng" was the inventor of movable type printing, which played a vital role in promoting the transmission of human knowledge. We hope that BISHENG can also provide strong support for the widespread implementation of intelligent applications. Everyone is welcome to participate.

AnyTool is an open-source universal tool-use layer for AI agents that addresses the critical problem of how autonomous agents reliably interact with external tools and environments. Rather than having each agent handle tool invocation logic on its own, AnyTool provides a standardized interface and orchestrator that intelligently selects and manages tools, reduces context overhead, and improves execution reliability across diverse capabilities like web APIs, local commands, and GUI...