At UC Berkeley, researchers in Sergey Levine's Robotic AI and Learning Lab eyed a table where a tower of 39 Jenga blocks stood perfectly stacked. Then a white-and-black robot, its single limb doubled over like a hunched-over giraffe, zoomed toward the tower, brandishing a black leather whip. Through what might have seemed to a casual viewer like a miracle of physics, the whip struck in precisely the right spot to send a single block flying from the stack while the rest of the tower remained structurally sound.
Modular robots built by Dartmouth researchers are finding their feet outdoors. Engineered to assemble into structures that best suit the task at hand, the robots are pieced together from cube-shaped robotic blocks that combine rigid rods and soft, stretchy strings whose tension can be adjusted to deform the blocks and control their shape.
Robots come in a vast array of shapes and sizes. By definition, they're machines that perform automatic tasks and can be operated by humans, but sometimes work autonomously—without human help.
Researchers from Scottish universities have developed an innovative way to breathe new life into outdated robot pets and toys using augmented reality technology.
For humanoid robots, size and weight are critical. The form factor must mimic human proportions while housing a complex network of sensors, motors and mechanical joints. This is where thin-section bearings prove essential.
While working at NASA in 2003, Dr. Robert Ambrose, director of the Robotics and Automation Design Lab (RAD Lab), designed a robot with no fixed top or bottom. A perfect sphere, the RoboBall could not flip over, and its shape promised access to places wheeled or legged machines could not reach—from the deepest lunar crater to the uneven sands of a beach.
The fastest way to stall an agentic AI project is to reuse a workflow that no longer fits. Using syftr, we identified “silver bullet” flows for both low-latency and high-accuracy priorities that consistently perform well across multiple datasets. These flows outperform random seeding and transfer learning early in optimization. They recover about 75% of the performance of a full syftr run at a fraction of the cost, which makes them a fast starting point but still leaves room to improve.
If you have ever tried to reuse an agentic workflow from one project in another, you know how often it falls flat. The model’s context length might not be enough. The new use case might require deeper reasoning. Or latency requirements might have changed.
Even when the old setup works, it may be overbuilt – and overpriced – for the new problem. In those cases, a simpler, faster setup might be all you need.
We set out to answer a simple question: Are there agentic flows that perform well across many use cases, so you can choose one based on your priorities and move forward?
Our research suggests the answer is yes, and we call them “silver bullets.”
We identified silver bullets for both low-latency and high-accuracy goals. In early optimization, they consistently beat transfer learning and random seeding, while avoiding the full cost of a full syftr run.
In the sections that follow, we explain how we found them and how they stack up against other seeding strategies.
A quick primer on Pareto-frontiers
You don’t need a math degree to follow along, but understanding the Pareto-frontier will make the rest of this post much easier to follow.
Figure 1 is an illustrative scatter plot – not from our experiments – showing completed syftr optimization trials. Sub-plot A and Sub-plot B are identical, but B highlights the first three Pareto-frontiers: P1 (red), P2 (green), and P3 (blue).
Each trial: A specific flow configuration is evaluated on accuracy and average latency (higher accuracy, lower latency are better).
Pareto-frontier (P1): No other flow has both higher accuracy and lower latency. These are non-dominated.
Non-Pareto flows: At least one Pareto flow beats them on both metrics. These are dominated.
P2, P3: If you remove P1, P2 becomes the next-best frontier, then P3, and so on.
You might choose between Pareto flows depending on your priorities (e.g., favoring low latency over maximum accuracy), but there’s no reason to choose a dominated flow — there’s always a better option on the frontier.
Optimizing agentic AI flows with syftr
Throughout our experiments, we used syftr to optimize agentic flows for accuracy and latency.
Set objectives such as accuracy and cost, or in this case, accuracy and latency
In short, syftr automates the exploration of flow configurations against your chosen objectives.
Figure 2 shows the high-level syftr architecture.
Figure 2: High-level syftr architecture. For a set of QA pairs, syftr can automatically explore agentic flows using multi-objective Bayesian optimization by comparing flow responses with actual answers.
Given the practically endless number of possible agentic flow parametrizations, syftr relies on two key techniques:
Multi-objective Bayesian optimization to navigate the search space efficiently.
ParetoPruner to stop evaluation of likely suboptimal flows early, saving time and compute while still surfacing the most effective configurations.
Silver bullet experiments
Our experiments followed a four-part process (Figure 3).
Figure 3: The workflow starts with a two-step data generation phase: A: Run syftr using simple random sampling for seeding. B: Run all finished flows on all other experiments. The resulting data then feeds into the next step. C: Identifying silver bullets and conducting transfer learning. D: Running syftr on four held-out datasets three times, using three different seeding strategies.
Step 1: Optimize flows per dataset
We ran several hundred trials on each of the following datasets:
CRAG Task 3 Music
FinanceBench
HotpotQA
MultihopRAG
For each dataset, syftr searched for Pareto-optimal flows, optimizing for accuracy and latency (Figure 4).
Figure 4: Optimization results for four datasets. Each dot represents a parameter combination evaluated on 50 QA pairs. Red lines mark Pareto-frontiers with the best accuracy–latency tradeoffs found by the TPE estimator.
Step 3: Identify silver bullets
Once we had identical flows across all training datasets, we could pinpoint the silver bullets — the flows that are Pareto-optimal on average across all datasets.
Figure 5: Silver bullet generation process, detailing the “Identify Silver Bullets” step from Figure 3.
Process:
Normalize results per dataset. For each dataset, we normalize accuracy and latency scores by the highest values in that dataset.
Group identical flows. We then group matching flows across datasets and calculate their average accuracy and latency.
Identify the Pareto-frontier. Using this averaged dataset (see Figure 6), we select the flows that build the Pareto-frontier.
These 23 flows are our silver bullets — the ones that perform well across all training datasets.
Figure 6: Normalized and averaged scores across datasets. The 23 flows on the Pareto-frontier perform well across all training datasets.
Step 4: Seed with transfer learning
In our original syftr paper, we explored transfer learning as a way to seed optimizations. Here, we compared it directly against silver bullet seeding.
In this context, transfer learning simply means selecting specific high-performing flows from historical (training) studies and evaluating them on held-out datasets. The data we use here is the same as for silver bullets (Figure 3).
Process:
Select candidates. From each training dataset, we took the top-performing flows from the top two Pareto-frontiers (P1 and P2).
Embed and cluster. Using the embedding model BAAI/bge-large-en-v1.5, we converted each flow’s parameters into numerical vectors. We then applied K-means clustering (K = 23) to group similar flows (Figure 7).
Match experiment constraints. We limited each seeding strategy (silver bullets, transfer learning, random sampling) to 23 flows for a fair comparison, since that’s how many silver bullets we identified.
Note: Transfer learning for seeding isn’t yet fully optimized. We could use more Pareto-frontiers, select more flows, or try different embedding models.
Figure 7: Clustered trials from Pareto-frontiers P1 and P2 across the training datasets.
Step 5: Testing it all
In the final evaluation phase (Step D in Figure 3), we ran ~1,000 optimization trials on four test datasets — Bright Biology, DRDocs, InfiniteBench, and PhantomWiki — repeating the process three times for each of the following seeding strategies:
Silver bullet seeding
Transfer learning seeding
Random sampling
For each trial, GPT-4o-mini served as the judge, verifying an agent’s response against the ground-truth answer.
Results
We set out to answer:
Which seeding approach — random sampling, transfer learning, or silver bullets — delivers the best performance for a new dataset in the fewest trials?
For each of the four held-out test datasets (Bright Biology, DRDocs, InfiniteBench, and PhantomWiki), we plotted:
Accuracy
Latency
Cost
Pareto-area: a measure of how close results are to the optimal result
In each plot, the vertical dotted line marks the point when all seeding trials have completed. After seeding, silver bullets showed on average:
9% higher maximum accuracy
84% lower minimum latency
28% larger Pareto-area
compared to the other strategies.
Bright Biology
Silver bullets had the highest accuracy, lowest latency, and largest Pareto-area after seeding. Some random seeding trials did not finish. Pareto-areas for all methods increased over time but narrowed as optimization progressed.
Figure 8: Bright Biology results
DRDocs
Similar to Bright Biology, silver bullets reached an 88% Pareto-area after seeding vs. 71% (transfer learning) and 62% (random).
Figure 9: DRDocs results
InfiniteBench
Other methods needed ~100 additional trials to match the silver bullet Pareto-area, and still didn’t match the fastest flows found via silver bullets by the end of ~1,000 trials.
Figure 10: InfiniteBench results
PhantomWiki
Silver bullets again performed best after seeding. This dataset showed the widest cost divergence. After ~70 trials, the silver bullet run briefly focused on more expensive flows.
Figure 11: PhantomWiki results
Pareto-fraction analysis
In runs seeded with silver bullets, the 23 silver bullet flows accounted for ~75% of the final Pareto-area after 1,000 trials, on average.
Red area: Gains from optimization over initial silver bullet performance.
Blue area: Silver bullet flows still dominating at the end.
Figure 12: Pareto-fraction for silver bullet seeding across all datasets
Our takeaway
Seeding with silver bullets delivers consistently strong results and even outperforms transfer learning, despite that method pulling from a diverse set of historical Pareto-frontier flows.
For our two objectives (accuracy and latency), silver bullets always start with higher accuracy and lower latency than flows from other strategies.
In the long run, the TPE sampler reduces the initial advantage. Within a few hundred trials, results from all strategies often converge, which is expected since each should eventually find optimal flows.
So, do agentic flows exist that work well across many use cases? Yes — to a point:
On average, a small set of silver bullets recovers about 75% of the Pareto-area from a full optimization.
Performance varies by dataset, such as 92% recovery for Bright Biology compared to 46% for PhantomWiki.
Bottom line: silver bullets are an inexpensive and efficient way to approximate a full syftr run, but they are not a replacement. Their impact could grow with more training datasets or longer training optimizations.
Here’s the full list of all 23 silver bullets, sorted from low accuracy / low latency to high accuracy / high latency: silver_bullets.json.
Try it yourself
Want to experiment with these parametrizations? Use the running_flows.ipynb notebook in our syftr repository — just make sure you have access to the models listed above.
For a deeper dive into syftr’s architecture and parameters, check out our technical paper or explore the codebase.
Nature, particularly humans and other animals, has always been among the primary sources of inspiration for roboticists. In fact, most existing robots physically resemble specific animals and/or are engineered to tackle tasks by emulating the actions, movements and behaviors of specific species.
In high-precision motion control systems like those used in precision manufacturing, the terms "sensor resolution" and "servo bandwidth" are often tossed around interchangeably, sometimes even confused as being functionally synonymous. But they're not.
You might have noticed that humanoid robots are having a bit of a moment. From Tesla's Optimus to Figure AI's Figure 02, these machines are no longer just science fiction—they're walking, and in some cases, cartwheeling into the real world.
In a world where automation is advancing by leaps and bounds, collaboration between robots is no longer science fiction. Imagine a warehouse where dozens of machines transport goods without colliding, a restaurant where robots serve dishes to the correct tables, or a factory where robot teams instantly adjust their tasks according to demand.
The rise of autonomous freight is more than a technological upgrade — it’s a fundamental shift in how goods move around the globe. Robotics innovations are rewriting the rules of efficiency, sustainability and safety.
Most existing robots designed to move on the ground rely on either wheels or legs, as opposed to a combination of the two. Yet robots that can seamlessly switch between wheeled and legged locomotion could be highly advantageous, as they could move more efficiently on a wider range of terrains, which could in turn contribute to the successful completion of missions.
The reason: ChatGPT-maker OpenAI is currently involved in a price war with one of its top competitors – Anthropic – in pricing that’s offered to volume users of AI, computer coders.
Observes Bort: “Some on X called OpenAI’s fees for the model ‘a pricing killer,’ while others on Hacker News are offering similar praise.”
Essentially, many users were turned-off by GPT-5’s initial personality, which was perceived as cold, distant and terse.
Observes writer Will Knight: “The backlash has sparked a fresh debate over the psychological attachments some users form with chatbots trained to push their emotional buttons.”
Observes Willson: “ChatGPT 5 is now one of the most powerful writing tools available, helping authors, bloggers, journalists, and content creators produce better work in less time.
“This model improves accuracy, expands creative depth, and introduces features that make writing easier, faster, and more engaging.”
*ChatGPT-5 Gets High Marks In Creative Writing: The Nerdy Novelist – a YouTube channel that closely tracks AI performance in fiction writing – is generally jazzed about the release of GPT-5.
Specifically, the channel’s testing finds that GPT-5 excels at generating imaginative and detailed prose.
Plus, compared to competitors like Claude 4 and Muse, GPT-5 offers more enhanced creative depth, versatility — as well s the ability to balance function with imagination.
Observes Orland: “Strictly by the numbers, GPT-5 ekes out a victory here, with the preferable response on four prompts to GPT-4o’s three prompts — with one tie.
“But on a majority of the prompts, which response was ‘better’ was more of a judgment call than a clear win.”
Observes writer Suzanne Blake: “AI has quickly shifted from a theoretical concept to a foundational aspect of education and workforce readiness.
“Nearly three-quarters of respondents reported that their schools have established AI usage policies, reflecting how students and institutions are adapting to new realities brought about by rapid technological change.”
*U.S. Federal Government Gets AI Subscriptions for a Buck: In what many consumers hope will be a long and bloody pricing war amidst the AI titans, Anthropic is now offering AI subscriptions to the U.S. federal government for one dollar.
The move comes after ChatGPT-maker OpenAI offered a similar deal to the feds.
One twist, according to writer Aishwarya Panda: “Reportedly, Anthropic is not only targeting the executive branch of the US government, but it will also offer $1 Claude AI subscription to the legislative and judiciary branches.”
Observes David Sharon, a Gemini Apps spokesperson: “To turn your photos into videos, select ‘Videos’ from the tool menu in the prompt box and upload a photo.
“Then, describe the scene and any audio instructions, and watch as your still image transforms into a dynamic video.”
A May 2025 study, for example, found that “Google’s Gemini Pro 2.5 failed at real-world office tasks 70% of the time,” according to writer Chris Taylor.
He adds: “It’s possible that ChatGPT agent will vault to the top of the reliability charts once it’s powered by GPT-5.”
Share a Link: Please consider sharing a link to https://RobotWritersAI.com from your blog, social media post, publication or emails. More links leading to RobotWritersAI.com helps everyone interested in AI-generated writing.
–Joe Dysart is editor of RobotWritersAI.com and a tech journalist with 20+ years experience. His work has appeared in 150+ publications, including The New York Times and the Financial Times of London.
Researchers have unveiled a new quantum material that could make quantum computers much more stable by using magnetism to protect delicate qubits from environmental disturbances. Unlike traditional approaches that rely on rare spin-orbit interactions, this method uses magnetic interactions—common in many materials—to create robust topological excitations. Combined with a new computational tool for finding such materials, this breakthrough could pave the way for practical, disturbance-resistant quantum computers.
