Sample Page Title

TL; DR

The quickest approach to stall an agentic AI challenge is to reuse a workflow that now not suits. Utilizing syftr, we recognized “silver bullet” flows for each low-latency and high-accuracy priorities that constantly carry out nicely throughout a number of datasets. These flows outperform random seeding and switch studying early in optimization. They get well about 75% of the efficiency of a full syftr run at a fraction of the associated fee, which makes them a quick place to begin however nonetheless leaves room to enhance.

When you’ve got ever tried to reuse an agentic workflow from one challenge in one other, you understand how typically it falls flat. The mannequin’s context size may not be sufficient. The brand new use case would possibly require deeper reasoning. Or latency necessities might need modified. 

Even when the previous setup works, it might be overbuilt – and overpriced – for the brand new drawback. In these circumstances, a less complicated, sooner setup is perhaps all you want. 

We got down to reply a easy query: Are there agentic flows that carry out nicely throughout many use circumstances, so you may select one primarily based in your priorities and transfer ahead?

Our analysis suggests the reply is sure, and we name them “silver bullets.” 

We recognized silver bullets for each low-latency and high-accuracy targets. In early optimization, they constantly beat switch studying and random seeding, whereas avoiding the complete value of a full syftr run.

Within the sections that comply with, we clarify how we discovered them and the way they stack up in opposition to different seeding methods.

 A fast primer on Pareto-frontiers

You don’t want a math diploma to comply with alongside, however understanding the Pareto-frontier will make the remainder of this publish a lot simpler to comply with. 

Determine 1 is an illustrative scatter plot – not from our experiments – displaying accomplished syftr optimization trials. Sub-plot A and Sub-plot B are equivalent, however B highlights the primary three Pareto-frontiers: P1 (pink), P2 (inexperienced), and P3 (blue).

• Every trial: A particular movement configuration is evaluated on accuracy and common latency (larger accuracy, decrease latency are higher).
• Pareto-frontier (P1): No different movement has each larger accuracy and decrease latency. These are non-dominated.
• Non-Pareto flows: At the least one Pareto movement beats them on each metrics. These are dominated.
• P2, P3: In case you take away P1, P2 turns into the next-best frontier, then P3, and so forth.

You would possibly select between Pareto flows relying in your priorities (e.g., favoring low latency over most accuracy), however there’s no purpose to decide on a dominated movement — there’s all the time a greater choice on the frontier.

Optimizing agentic AI flows with syftr

All through our experiments, we used syftr to optimize agentic flows for accuracy and latency. 

This strategy lets you:

• Choose datasets containing query–reply (QA) pairs
• Outline a search area for movement parameters
• Set aims similar to accuracy and value, or on this case, accuracy and latency

Briefly, syftr automates the exploration of movement configurations in opposition to your chosen aims.

Determine 2 reveals the high-level syftr structure.

Given the virtually limitless variety of potential agentic movement parametrizations, syftr depends on two key strategies:

• Multi-objective Bayesian optimization to navigate the search area effectively.
• ParetoPruner to cease analysis of doubtless suboptimal flows early, saving time and compute whereas nonetheless surfacing the best configurations.

Silver bullet experiments

Our experiments adopted a four-part course of (Determine 3).

Step 1: Optimize flows per dataset

We ran a number of hundred trials on every of the next datasets:

• CRAG Activity 3 Music
• FinanceBench
• HotpotQA
• MultihopRAG

For every dataset, syftr looked for Pareto-optimal flows, optimizing for accuracy and latency (Determine 4).

Step 3: Determine silver bullets

As soon as we had equivalent flows throughout all coaching datasets, we might pinpoint the silver bullets — the flows which might be Pareto-optimal on common throughout all datasets.

Course of:

1. Normalize outcomes per dataset.  For every dataset, we normalize accuracy and latency scores by the best values in that dataset.
2. Group equivalent flows. We then group matching flows throughout datasets and calculate their common accuracy and latency.
3. Determine the Pareto-frontier. Utilizing this averaged dataset (see Determine 6), we choose the flows that construct the Pareto-frontier. 

These 23 flows are our silver bullets — those that carry out nicely throughout all coaching datasets.

Step 4: Seed with switch studying

In our unique syftr paper, we explored switch studying as a approach to seed optimizations. Right here, we in contrast it immediately in opposition to silver bullet seeding.

On this context, switch studying merely means choosing particular high-performing flows from historic (coaching) research and evaluating them on held-out datasets. The information we use right here is identical as for silver bullets (Determine 3).

Course of:

1. Choose candidates. From every coaching dataset, we took the top-performing flows from the highest two Pareto-frontiers (P1 and P2).
2. Embed and cluster. Utilizing the embedding mannequin BAAI/bge-large-en-v1.5, we transformed every movement’s parameters into numerical vectors. We then utilized Okay-means clustering (Okay = 23) to group comparable flows (Determine 7).
3. Match experiment constraints. We restricted every seeding technique (silver bullets, switch studying, random sampling) to 23 flows for a good comparability, since that’s what number of silver bullets we recognized.

Word: Switch studying for seeding isn’t but totally optimized. We might use extra Pareto-frontiers, choose extra flows, or strive completely different embedding fashions.

Step 5: Testing all of it

Within the remaining analysis part (Step D in Determine 3), we ran ~1,000 optimization trials on 4 check datasets — Shiny Biology, DRDocs, InfiniteBench, and PhantomWiki — repeating the method thrice for every of the next seeding methods:

• Silver bullet seeding
• Switch studying seeding
• Random sampling

For every trial, GPT-4o-mini served because the decide, verifying an agent’s response in opposition to the ground-truth reply.

Outcomes

We got down to reply:

Which seeding strategy — random sampling, switch studying, or silver bullets — delivers the most effective efficiency for a brand new dataset within the fewest trials?

For every of the 4 held-out check datasets (Shiny Biology, DRDocs, InfiniteBench, and PhantomWiki), we plotted:

• Accuracy
• Latency
• Price
• Pareto-area: a measure of how shut outcomes are to the optimum consequence

In every plot, the vertical dotted line marks the purpose when all seeding trials have accomplished. After seeding, silver bullets confirmed on common:

• 9% larger most accuracy
• 84% decrease minimal latency
• 28% bigger Pareto-area

in comparison with the opposite methods.

Shiny Biology

Silver bullets had the best accuracy, lowest latency, and largest Pareto-area after seeding. Some random seeding trials didn’t end. Pareto-areas for all strategies elevated over time however narrowed as optimization progressed.

DRDocs

Much like Shiny Biology, silver bullets reached an 88% Pareto-area after seeding vs. 71% (switch studying) and 62% (random).

InfiniteBench

Different strategies wanted ~100 extra trials to match the silver bullet Pareto-area, and nonetheless didn’t match the quickest flows discovered by way of silver bullets by the top of ~1,000 trials.

PhantomWiki

Silver bullets once more carried out greatest after seeding. This dataset confirmed the widest value divergence. After ~70 trials, the silver bullet run briefly targeted on dearer flows.

Pareto-fraction evaluation

In runs seeded with silver bullets, the 23 silver bullet flows accounted for ~75% of the ultimate Pareto-area after 1,000 trials, on common.

• Pink space: Beneficial properties from optimization over preliminary silver bullet efficiency.
• Blue space: Silver bullet flows nonetheless dominating on the finish.

Our takeaway

Seeding with silver bullets delivers constantly sturdy outcomes and even outperforms switch studying, regardless of that technique pulling from a various set of historic Pareto-frontier flows. 

For our two aims (accuracy and latency), silver bullets all the time begin with larger accuracy and decrease latency than flows from different methods.

In the long term, the TPE sampler reduces the preliminary benefit. Inside a number of hundred trials, outcomes from all methods typically converge, which is predicted since every ought to finally discover optimum flows.

So, do agentic flows exist that work nicely throughout many use circumstances? Sure — to some extent:

• On common, a small set of silver bullets recovers about 75% of the Pareto-area from a full optimization.
• Efficiency varies by dataset, similar to 92% restoration for Shiny Biology in comparison with 46% for PhantomWiki.

Backside line: silver bullets are a reasonable and environment friendly approach to approximate a full syftr run, however they aren’t a alternative. Their affect might develop with extra coaching datasets or longer coaching optimizations.

 Silver bullet parametrizations

We used the next:

LLMs

• microsoft/Phi-4-multimodal-instruct
• deepseek-ai/DeepSeek-R1-Distill-Llama-70B
• Qwen/Qwen2.5
• Qwen/Qwen3-32B
• google/gemma-3-27b-it
• nvidia/Llama-3_3-Nemotron-Tremendous-49B

Embedding fashions

• BAAI/bge-small-en-v1.5
• thenlper/gte-large
• mixedbread-ai/mxbai-embed-large-v1
• sentence-transformers/all-MiniLM-L12-v2
• sentence-transformers/paraphrase-multilingual-mpnet-base-v2
• BAAI/bge-base-en-v1.5
• BAAI/bge-large-en-v1.5
• TencentBAC/Conan-embedding-v1
• Linq-AI-Analysis/Linq-Embed-Mistral
• Snowflake/snowflake-arctic-embed-l-v2.0
• BAAI/bge-multilingual-gemma2

Circulate varieties

• vanilla RAG
• ReAct RAG agent
• Critique RAG agent
• Subquestion RAG

Right here’s the complete record of all 23 silver bullets, sorted from low accuracy / low latency to excessive accuracy / excessive latency: silver_bullets.json. 

Attempt it your self

Need to experiment with these parametrizations? Use the running_flows.ipynb pocket book in our syftr repository — simply be sure you have entry to the fashions listed above. 

For a deeper dive into syftr’s structure and parameters, take a look at our technical paper or discover the codebase.

We’ll even be presenting this work on the Worldwide Convention on Automated Machine Studying (AutoML) in September 2025 in New York Metropolis.