SalesforceAIResearch

Unified Training of Universal Time Series Forecasting Transformers

Salesforce Enterprise Deep Research

An Automatic Prompt Optimization Framework for Large Language Models

Code for "Diffusion Model Alignment Using Direct Preference Optimization"

xLAM: A Family of Large Action Models to Empower AI Agent Systems

MCP-Universe is a comprehensive framework designed for RL training, benchmarking, and developing AI agents for general tool-use.

Official Repo for CRMArena and CRMArena-Pro

MCP-based Agent Deep Evaluation System

The raw UserRL repo under construction

Designing Multi-Agent Systems with Zero Supervision

A live benchmark and evaluation framework for open-ended deep research in the wild.

Agent Development Life Cycle — Build, deploy, test, and optimize Agentforce agents using Claude Code skills and Agent Script DSL.

Beagle is designed to be the unified platform for the broader Recursive Self-Improvement (RSI) ecosystem. Think of it as Hugging Face Trainer for agent evolution. Its efficient rollout engine...

Code for WALT – Web Agents that Learn Tools

An automated data pipeline scaling RL to pretraining levels

Code for the paper "Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning" https://arxiv.org/abs/2609.03430

Salesforce AI Research's open diffusion language model

Make reasoning models scalable