You’re not brief on instruments. Or fashions. Or frameworks.
What you’re brief on is a principled method 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 doable workflows, leading to a search house with over 10²³ doable configurations.
Trial-and-error doesn’t scale. And model-level benchmarks don’t replicate how elements behave when stitched into full methods.
That’s why we constructed syftr — an open supply framework for mechanically figuring out Pareto-optimal workflows throughout accuracy, price, and latency constraints.
See syftr in motion
Need a fast walkthrough earlier than diving in? This brief demo exhibits how syftr works to assist AI groups effectively discover generative AI workflow configurations and floor high-performing choices.
The complexity behind generative AI workflows
For instance how shortly complexity compounds, take into account even a comparatively easy RAG pipeline just like the one proven in Determine 1.
Every element—retriever, immediate technique, embedding mannequin, textual content splitter, synthesizing LLM—requires cautious choice and tuning. And past these selections, 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 may be not possible 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 sturdy tradeoffs throughout key efficiency metrics.
The instance beneath exhibits syftr’s output on the CRAG (Complete RAG) Sports activities benchmark, highlighting workflows that keep excessive accuracy whereas considerably decreasing price.
Whereas Determine 2 exhibits 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 Area, 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 element — albeit a vital one — inside bigger, subtle AI methods.
Measuring intrinsic mannequin efficiency is important, nevertheless it leaves open important system-level questions:
- How do you assemble a workflow that meets task-specific targets for accuracy, latency, and price?
- Which fashions do you have to use—and by which components of the pipeline?
syftr addresses this hole by enabling automated, multi-objective analysis throughout complete 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 mechanically determine Pareto-optimal generative AI workflows that steadiness a number of competing targets concurrently — not simply accuracy, however latency and price as nicely.
It attracts inspiration from current 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 among our core analysis inspirations.
Importantly, syftr can also be orthogonal to LLM-as-optimizer frameworks like Hint and TextGrad, and generic move optimizers like DSPy. Such frameworks will 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 beneficial properties counsel that post-hoc immediate optimization can meaningfully increase 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 increasing 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 latest 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 numerous highly effective open supply libraries and frameworks:
- Ray for distributing and scaling search over giant clusters of CPUs and GPUs
- Ray Serve for autoscaling mannequin internet hosting
- Optuna for its versatile define-by-run interface (much like PyTorch’s keen execution) and assist 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, similar to prompts
syftr is framework-agnostic: workflows will 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 examine: 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:
- Process 1: Retrieval summarization
- Process 2: Information graph and internet retrieval
- Process 3: Finish-to-end RAG
syftr was evaluated on Process 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 sensible, difficult retrieval setting.
Observe: 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 sooner and cheaper, main the optimizer to favor these configurations extra incessantly than agentic ones.
- GPT-4o-mini incessantly seems in Pareto-optimal flows, suggesting it provides a powerful steadiness of high quality and price as a synthesizing LLM.
- Reasoning fashions like o3-mini carry out nicely on quantitative duties (e.g., FinanceBench, InfiniteBench), probably resulting from 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 only a few proportion 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.
Price of operating syftr
In our experiments, we allotted a price range of ~500 workflow evaluations per activity. Though actual prices differ based mostly on the dataset and search house complexity, we constantly recognized sturdy Pareto frontiers with a one-time search price of roughly $500 per use case.
We count on 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 beneficial properties from deploying optimized workflows, whether or not by means of decreased compute utilization, improved accuracy, or higher consumer expertise in high-traffic methods.
For detailed outcomes throughout six benchmark duties, together with datasets past CRAG, check 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 common immediate methods
- 3 retrievers
- 4 textual content splitters (with parameter configurations)
- 4 agentic RAG flows and 1 non-agentic RAG move, every with related hierarchical hyperparameters
New elements, similar to fashions, flows, or search modules, will be added or modified by way of configuration information. Detailed walkthroughs can be found to assist customization.
syftr is developed totally within the open. We welcome contributions by way of pull requests, function proposals, and benchmark studies. We’re significantly concerned with concepts that advance the analysis course or enhance the framework’s extensibility.
What’s forward for syftr
syftr continues to be evolving, with a number of lively areas of analysis designed to increase its capabilities and sensible impression:
- Meta-learning
At the moment, every search is carried out from scratch. We’re exploring meta-learning strategies that leverage prior runs throughout related duties to speed up and information future searches. - Multi-agent workflow analysis
Whereas multi-agent methods are gaining traction, they introduce extra complexity and price. We’re investigating how these workflows evaluate 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 methods 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 develop syftr’s activity repertoire to code era, information evaluation, and interpretation. We additionally invite the neighborhood to counsel extra duties for syftr to prioritize.
As these efforts progress, we purpose to develop 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.
Strive the code, learn the analysis
To discover syftr additional, try the GitHub repository or learn the total 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 stay up for seeing what you construct and discovering what’s subsequent, collectively.
