You’re not quick on instruments. Or fashions. Or frameworks.
What you’re quick on is a principled approach to make use of them — at scale.
Constructing efficient generative AI workflows, particularly agentic ones, means navigating a combinatorial explosion of selections.
Each new retriever, immediate technique, textual content splitter, embedding mannequin, or synthesizing LLM multiplies the house of potential workflows, leading to a search house with over 10²³ potential configurations.
Trial-and-error doesn’t scale. And model-level benchmarks don’t mirror how elements behave when stitched into full programs.
That’s why we constructed syftr — an open supply framework for robotically figuring out Pareto-optimal workflows throughout accuracy, price, and latency constraints.
The complexity behind generative AI workflows
As an example how rapidly complexity compounds, think about even a comparatively easy RAG pipeline just like the one proven in Determine 1.
Every part—retriever, immediate technique, embedding mannequin, textual content splitter, synthesizing LLM—requires cautious choice and tuning. And past these choices, there’s an increasing panorama of end-to-end workflow methods, from single-agent workflows like ReAct and LATS to multi-agent workflows like CaptainAgent and Magentic-One.
What’s lacking is a scalable, principled approach to discover this configuration house.
That’s the place syftr is available in.
Its open supply framework makes use of multi-objective Bayesian Optimization to effectively seek for Pareto-optimal RAG workflows, balancing price, accuracy, and latency throughout configurations that will be unattainable to check manually.
Benchmarking Pareto-optimal workflows with syftr
As soon as syftr is utilized to a workflow configuration house, it surfaces candidate pipelines that obtain robust tradeoffs throughout key efficiency metrics.
The instance under reveals syftr’s output on the CRAG (Complete RAG) Sports activities benchmark, highlighting workflows that keep excessive accuracy whereas considerably decreasing price.
Whereas Determine 2 reveals what syftr can ship, it’s equally vital to grasp how these outcomes are achieved.
On the core of syftr is a multi-objective search course of designed to effectively navigate huge workflow configuration areas. The framework prioritizes each efficiency and computational effectivity – important necessities for real-world experimentation at scale.
Since evaluating each workflow on this house isn’t possible, we sometimes consider round 500 workflows per run.
To make this course of much more environment friendly, syftr features a novel early stopping mechanism — Pareto Pruner — which halts analysis of workflows which can be unlikely to enhance the Pareto frontier. This considerably reduces computational price and search time whereas preserving outcome high quality.
Why present benchmarks aren’t sufficient
Whereas mannequin benchmarks, like MMLU, LiveBench, Chatbot Enviornment, and the Berkeley Operate-Calling Leaderboard, have superior our understanding of remoted mannequin capabilities, basis fashions not often function alone in real-world manufacturing environments.
As an alternative, they’re sometimes one part — albeit a vital one — inside bigger, subtle AI programs.
Measuring intrinsic mannequin efficiency is important, nevertheless it leaves open important system-level questions:
- How do you assemble a workflow that meets task-specific objectives for accuracy, latency, and value?
- Which fashions do you have to use—and during which components of the pipeline?
syftr addresses this hole by enabling automated, multi-objective analysis throughout total workflows.
It captures nuanced tradeoffs that emerge solely when elements work together inside a broader pipeline, and systematically explores configuration areas which can be in any other case impractical to judge manually.
syftr is the primary open-source framework particularly designed to robotically establish Pareto-optimal generative AI workflows that stability a number of competing goals concurrently — not simply accuracy, however latency and value as properly.
It attracts inspiration from present analysis, together with:
- AutoRAG, which focuses solely on optimizing for accuracy
- Kapoor et al. ‘s work, AI Brokers That Matter, which emphasizes cost-controlled analysis to stop incentivizing overly expensive, leaderboard-focused brokers. This precept serves as one in all our core analysis inspirations.
Importantly, syftr can also be orthogonal to LLM-as-optimizer frameworks like Hint and TextGrad, and generic movement optimizers like DSPy. Such frameworks may be mixed with syftr to additional optimize prompts in workflows.
In early experiments, syftr first recognized Pareto-optimal workflows on the CRAG Sports activities benchmark.
We then utilized Hint to optimize prompts throughout all of these configurations — taking a two-stage method: multi-objective workflow search adopted by fine-grained immediate tuning.
The outcome: notable accuracy enhancements, particularly in low-cost workflows that originally exhibited decrease accuracy (these clustered within the lower-left of the Pareto frontier). These good points counsel that post-hoc immediate optimization can meaningfully enhance efficiency, even in extremely cost-constrained settings.
This two-stage method — first multi-objective configuration search, then immediate refinement — highlights the advantages of mixing syftr with specialised downstream instruments, enabling modular and versatile workflow optimization methods.
Constructing and lengthening syftr’s search house
Syftr cleanly separates the workflow search house from the underlying optimization algorithm. This modular design permits customers to simply lengthen or customise the house, including or eradicating flows, fashions, and elements by enhancing configuration information.
The default implementation makes use of Multi-Goal Tree-of-Parzen-Estimators (MOTPE), however syftr helps swapping in different optimization methods.
Contributions of recent flows, modules, or algorithms are welcomed by way of pull request at github.com/datarobot/syftr.
Constructed on the shoulders of open supply
syftr builds on a lot of highly effective open supply libraries and frameworks:
- Ray for distributing and scaling search over massive clusters of CPUs and GPUs
- Ray Serve for autoscaling mannequin internet hosting
- Optuna for its versatile define-by-run interface (just like PyTorch’s keen execution) and help for state-of-the-art multi-objective optimization algorithms
- LlamaIndex for constructing subtle agentic and non-agentic RAG workflows
- HuggingFace Datasets for quick, collaborative, and uniform dataset interface
- Hint for optimizing textual elements inside workflows, equivalent to prompts
syftr is framework-agnostic: workflows may be constructed utilizing any orchestration library or modeling stack. This flexibility permits customers to increase or adapt syftr to suit all kinds of tooling preferences.
Case research: syftr on CRAG Sports activities
Benchmark setup
The CRAG benchmark dataset was launched by Meta for the KDD Cup 2024 and consists of three duties:
- Job 1: Retrieval summarization
- Job 2: Information graph and net retrieval
- Job 3: Finish-to-end RAG
syftr was evaluated on Job 3 (CRAG3), which incorporates 4,400 QA pairs spanning a variety of matters. The official benchmark performs RAG over 50 webpages retrieved for every query.
To extend issue, we mixed all webpages throughout all questions right into a single corpus, making a extra reasonable, difficult retrieval setting.
Word: Amazon Q pricing makes use of a per-user/month pricing mannequin, which differs from the per-query token-based price estimates used for syftr workflows.
Key observations and insights
Throughout datasets, syftr constantly surfaces significant optimization patterns:
- Non-agentic workflows dominate the Pareto frontier. They’re quicker and cheaper, main the optimizer to favor these configurations extra steadily than agentic ones.
- GPT-4o-mini steadily seems in Pareto-optimal flows, suggesting it provides a robust stability of high quality and value as a synthesizing LLM.
- Reasoning fashions like o3-mini carry out properly on quantitative duties (e.g., FinanceBench, InfiniteBench), doubtless on account of their multi-hop reasoning capabilities.
- Pareto frontiers ultimately flatten after an preliminary rise, with diminishing returns in accuracy relative to steep price will increase, underscoring the necessity for instruments like syftr that assist pinpoint environment friendly working factors.
We routinely discover that the workflow on the knee level of the Pareto frontier loses just some share factors in accuracy in comparison with probably the most correct setup — whereas being 10x cheaper.
syftr makes it straightforward to seek out that candy spot.
Value of working syftr
In our experiments, we allotted a price range of ~500 workflow evaluations per job. Though precise prices differ based mostly on the dataset and search house complexity, we constantly recognized robust Pareto frontiers with a one-time search price of roughly $500 per use case.
We anticipate this price to lower as extra environment friendly search algorithms and house definitions are developed.
Importantly, this preliminary funding is minimal relative to the long-term good points from deploying optimized workflows, whether or not by way of diminished compute utilization, improved accuracy, or higher person expertise in high-traffic programs.
For detailed outcomes throughout six benchmark duties, together with datasets past CRAG, consult with the full syftr paper.
Getting began and contributing
To get began with syftr, clone or fork the repository on GitHub. Benchmark datasets can be found on HuggingFace, and syftr additionally helps user-defined datasets for customized experimentation.
The present search house consists of:
- 9 proprietary LLMs
- 11 embedding fashions
- 4 normal immediate methods
- 3 retrievers
- 4 textual content splitters (with parameter configurations)
- 4 agentic RAG flows and 1 non-agentic RAG movement, every with related hierarchical hyperparameters
New elements, equivalent to fashions, flows, or search modules, may be added or modified by way of configuration information. Detailed walkthroughs can be found to help customization.
syftr is developed totally within the open. We welcome contributions by way of pull requests, function proposals, and benchmark experiences. We’re notably keen on concepts that advance the analysis path or enhance the framework’s extensibility.
What’s forward for syftr
syftr continues to be evolving, with a number of energetic areas of analysis designed to increase its capabilities and sensible affect:
- Meta-learning
Presently, every search is carried out from scratch. We’re exploring meta-learning strategies that leverage prior runs throughout comparable duties to speed up and information future searches. - Multi-agent workflow analysis
Whereas multi-agent programs are gaining traction, they introduce extra complexity and value. We’re investigating how these workflows examine to single-agent and non-agentic pipelines, and when their tradeoffs are justified. - Composability with immediate optimization frameworks
syftr is complementary to instruments like DSPy, Hint, and TextGrad, which optimize textual elements inside workflows. We’re exploring methods to extra deeply combine these programs to collectively optimize construction and language. - Extra agentic duties
We began with question-answer duties, a important manufacturing use case for brokers. Subsequent, we plan to quickly broaden syftr’s job repertoire to code technology, knowledge evaluation, and interpretation. We additionally invite the group to counsel extra duties for syftr to prioritize.
As these efforts progress, we goal to broaden syftr’s worth as a analysis instrument, a benchmarking framework, and a sensible assistant for system-level generative AI design.
In the event you’re working on this house, we welcome your suggestions, concepts, and contributions.
Attempt the code, learn the analysis
To discover syftr additional, try the GitHub repository or learn the complete paper on ArXiv for particulars on methodology and outcomes.
Syftr has been accepted to look on the Worldwide Convention on Automated Machine Studying (AutoML) in September, 2025 in New York Metropolis.
We sit up for seeing what you construct and discovering what’s subsequent, collectively.