SFR-AutoR&D: autonomous research and development from Salesforce AI Research

How SFR-AutoR&D works

Start with an R&D goal, an artifact to work on, and a budget. The agent develops a method, tests it, and uses the evidence to decide what comes next.

Input

A research goal

What could work better?

ArtifactRepository or model

TargetA measurable gain

BoundsBudget & constraints

SFR-AutoR&D Autonomous R&D

Output

Verified progress

A better solution, with proof.

A new method
Patch or checkpoint
Reproducible evidence

Today, we’re introducing two specialized R&D agents.

SFR-AutoR&D

AutoR&D-Engineer

Explore AutoR&D-Engineer

Discover better methods. Implement them. Prove the improvement.

Input Repository + research goalSystem, target & constraints

AutoR&D-Engineer

Output Verified implementationPatch + benchmark evidence

Research highlights

pandasNullable-dtype reductionsup to1.84×faster reductions Salesforce SFR-RLTwo improvements · separate workloads Serving · up to3.14×generated tokens / secondTraining−39%peak training memory

Vector search

USearchSingle-core · GCC 11 · 1M vectors+17.5%more queries / second hnswlibMedian across 3 index builds+4.1%more queries / second

Gains are measured against each workload’s baseline. Open a result for its setup, correctness checks, and benchmark evidence.

SFR-AutoR&D

TrainForge

Explore TrainForge

Invent training methods. Run the experiments. Keep the best model.

Input Baseline model + targetTask, evaluation & compute budget

TrainForge

Output Best verified checkpointModel + evaluation record

Research highlights

GPT-OSS-20BResearch quality · prior harness experimentsup to+11percentage points Qwen3-4B · end-to-end demoDemonstrated run · adapter reproduced from disk Training20optimizer updatesCompute1 H200GPU

Training programs in progress

ResearchMathCodingMultilingual reasoning

The gain of up to 11 percentage points comes from prior harness experiments. Other program results are forthcoming. If no candidate improves, the baseline stays.

Shared training infrastructure

AutoInfra supports the research loop.

AutoInfra provides shared training and inference infrastructure for SFR-AutoR&D. TrainForge uses it to launch and compare model experiments in parallel. It also supports training the models that power TrainForge and AutoR&D-Engineer, while validated improvements from either agent can be incorporated into AutoInfra for the next research cycle.

Explore AutoInfra

What it means in practice and for Salesforce.

Improve codebases and solutions

Use AutoR&D-Engineer to discover and implement better algorithms in existing systems, from data pipelines to retrieval engines. Validate gains in speed and memory efficiency while preserving correctness.

Train better models

Use AutoR&D-TrainForge to explore training methods and optimizers through controlled experiments. Identify what improves model quality and training efficiency within a defined compute budget.

Advance scientific discovery in AI Research

Use AutoR&D to explore open research questions, form hypotheses, and develop new algorithms and methods. Help Salesforce AI Research turn promising ideas into reproducible findings that inform the next experiment.