Training Example: Los Alamos National Laboratory – Review the Data, Give Your Score & Compare to the Real AI Evaluation

[IMG: upgrading Los Alamos National Laboratory]
[H1] The Lab is prepared for wildfire season
Learn how the Lab clears potential wildfire fuels, safely stores waste, monitors the air and takes other steps to prevent wildfire and protect the community.
[IMG: 3 participants at the event]
ScienceAdvancing LANL's AI mission: Los Alamos scientists team up
[IMG: Curiosity discovered unexpected signs of an ancient lake]
ScienceAncient lakes on Mars: NASA's Curiosity rover finds more evidence
[IMG: drawing of TA-3 area]
The LabInjuries at Los Alamos continue steady decline
[IMG: night view of lab]
The LabPit production: Meeting the needs of the nation
[IMG: URSA bear logo]
ScienceURSA is AI agent transforming how science gets done
[H2] Our mission
Los Alamos National Laboratory addresses national security challenges by advancing breakthroughs in science and technology. We work alongside the Department of Energy to support energy advancements and environmental management.Learn more about our mission
[H2] Explore our science in action
[IMG: silicone foams created by 3D]
[H3] Tailoring 3D-printed foams to meet national security missions
Additive manufacturing, high-throughput testing and machine learning combined
[H4] NASA's Curiosity rover finds more evidence of ancient lakes on Mars
The findings shed new light on the potential for past life.
[H4] Dynamic imaging at Los Alamos: Look inside extreme physics
Techniques like proton radiography let scientists to see deep inside experiments in fractions of a second.
[H4] Lab launches frontier AI models on Venado supercomputer
Supercomputer running latest OpenAI reasoning models on NVIDIA Grace Hopper GPUs to accelerate national security-related science.
[H4] URSA is AI agent transforming how science gets done
Framework is built to bring AI into the heart of scientific discovery.
[H2] Los Alamos National Lab at a glance
[H3] 10
Research facilities
[H3] $2.7 million
To nonprofits in 2025 Employee Giving Campaign
[H3] 65
Awards, honors in 2025
[H3] 27
Cultural resource projects
[H2] From the top of the mesa
We are 18,000+ people in New Mexico and beyond, with a shared goal to serve the common good.
[IMG: Community garden]
[H2] Community
[IMG: Safety protection PPE]
[H2] Safety
[IMG: Collaborate]
[H2] Collaborate
[H2] Featured news
All news
[IMG: scenario-based training exercise]
[H3] Los Alamos strengthens safety through partnership and realistic training
Community collaboration provides incredible experience.
[IMG: person welding at the Lab]
[H4] 6 ways New Mexico colleges connect you with Lab careers
[IMG: STEMarts Lab in Taos]
[H4] LANL Foundation awards over $100,000 in grants to support STEAM education
[IMG: Rendija Canyon]
[H4] 4 ways Los Alamos stewards our site and community
[IMG: Rich Nieto and team looking at wildfire map]
[H4] The Lab mitigates wildfire year-round
NewsPublicationsPodcastsVideos
[H2] Voices of the Lab
Los Alamos National Laboratory is one of the world’s most innovative multidisciplinary research institutions.
[IMG: Grant Martin]
[H3] Boston Marathon runners
Employees
[IMG: Ed Anderson]
[H3] Ed Anderson
Operations
[IMG: Photo of Hermelinda Coronado]
[H3] Hermelinda Coronado
Janitor
[IMG: Photo of Fatima Woody]
[H3] Fatima Woody
Computer Systems
[IMG: Photo of Vernon Vigil]
[H3] Vernon Vigil
Engineering Technologist
[IMG: Photo of Aaron Couture]
[H3] Aaron Couture
Experimental Nuclear Astrophysicist
[IMG: Opperations support]
[H2] Start your career with us
You don’t need to be a scientist or engineer to work at the Lab. We offer a vast array of career opportunities for a variety of skill sets.Start Search
[H2] Explore our history
We have a proud history of almost 80 years of science and innovation to protect the nation.
[IMG: A photo of some of the displays in the Bradbury Science Museum]
[H2] Bradbury Science Museum
[IMG: The outside of the National Security Research Center building]
[H2] National Security Research Center
[IMG: Old photo of the original Main Gate house for the Los Alamos Project]
[H2] Manhattan Project National Historic Park
[H2] Follow us
Keep up with the latest news from the Lab.Visit Los Alamos National Laboratory Facebook PageVisit Los Alamos National Laboratory on X (formerly Twitter)Visit Los Alamos National Laboratory LinkedIn PageVisit Los Alamos National Laboratory Instagram PageVisit Los Alamos National Laboratory YouTube Channel
[IMG: Black and white photo of Oppenheimer talking to General Groves]
[IMG: Scenic view of New Mexico hills with two hikers standing in the foreground facing the hills]
[IMG: A Los Alamos National Laboratory scientist using scientific equipment.]

[IMG: Wildfire Main Banner]
[H1] Wildfire Preparedness
[H2] Los Alamos National Laboratory is prepared for wildfire season
[H3] Comprehensive, year-round fire mitigation in Los Alamos and beyond
Learn more about how the Lab clears potential wildfire fuels, safely stores waste, monitors the air and takes other steps to prevent wildfire and protect the community.
[H3] Protecting the Laboratory against fire
The Lab has performed extensive and strategic wildfire mitigation work over the last two decades, ensuring we are well prepared.Learn More
[H3] Safe storage of materials
See how the Lab ensures waste is stored safely and away from the potential path of wildfire.Learn More
[H3] Continuous air monitoring
Thanks to 68 air monitoring sites, the Lab is one of the most thoroughly monitored environments in the world.Learn More
[H3] Understanding radiation
There is no more risk of radiation spread at the Laboratory than anywhere else in New Mexico.Learn More
[H3] In the event of an evacuation
Processes and procedures are in place should a wildfire happen to advance.Learn More
[H3] Los Alamos National Laboratory: Fast facts
How big is the Lab? Where is it located? What is the total workforce? Find answers here.Learn More
[H2] Related Videos
All Videos1:38
[H3] Fire Mitigation Efforts at LANL
Watch Now2:12
[H3] Wildland Fire Mitigation
Watch Now1:27
[H3] Fighting Fire with Software
Watch Now2:53
[H3] Radiation Protection
Watch Now3:03
[H3] When Wildfire Meets Water: It's Complicated
Watch Now2:28
[H3] Water Quality Protection
Watch Now2:40
[H3] The Air Quality Monitoring Network
Watch Now
[H3] Who to contact
For media questions and inquiriesContact Us

April 21, 2026
[H1] NASA’s Curiosity Rover finds more evidence of ancient lakes on Mars
[H2] The findings shed new light on the potential for past life
[IMG: 2026-04-21]
A NASA “postcard” of the Amapari Marker Band, a winding region where Curiosity discovered unexpected signs of an ancient lake. Credit to: NASA/JPL-CaltechA team of scientists using the ChemCam instrument on NASA’s Curiosity Mars rover has discovered the highest amounts of iron, manganese, and zinc ever found together in the Gale Crater on Mars. Minerals with these metals were found in remarkably well-preserved ripples in rocks, indicating the high likelihood that a shallow lake existed at this location.Metal-rich deposits form in lakes on Earth by chemical reactions called “redox (reduction-oxidation) reactions” in places that are almost always inhabited by microbes. Finding similar environments on Mars is exciting because it means that Gale Crater was home to an ancient lake that had favorable conditions for past life.“The metals were found in preserved ripples, which is the clearest evidence we have that a lake was present in Gale Crater. But what’s more surprising is that this lake existed high up on Mount Sharp, where the rover explored rocks that were deposited during an era on Mars when the climate was drying out,” said Patrick Gasda, ChemCam Instrument science team member and research scientist at Los Alamos National Laboratory. “Ancient Mars was much wetter, and lakes in craters were common then. It seems that as Mars became drier and colder, lakes that formed less frequently were very short-lived.”ChemCam uses a technique called “laser-induced breakdown spectroscopy” to zap rocks to create a plasma and then collects the light from that plasma to understand what elements are present on the planet’s surface. Its goal is to establish past habitability on Mars, addressing the question of whether Mars was once suitable for life. The ChemCam instrument was built and is operated by a partnership between Los Alamos and the Institut de Recherche en Astrophysique et Planétologie (IRAP), funded by the French space agency CNES. The rover was built and is operated by NASA’s Jet Propulsion Laboratory.Curiosity has recently been exploring a large sedimentary mound that researchers believe shows the transition from a warm and wet (phyllosilicate-rich) to a cold and drier (sulfate-rich) Mars.
[H3] Implications for past life on Mars
The discovery of redox-active metals such as iron and manganese could indicate that life would have thrived in this lake, if life existed on Mars. Some forms of microbial life on Earth can use these metals as energy sources. The fact that these metals were found in the Amapari Marker Band suggests that even as Mars dried out, there were still isolated pockets of water where microbial life could have survived.These iron, manganese, and zinc deposits can lay the groundwork for future research on the red planet. They can help researchers decide where Curiosity should explore next or determine locations for potential sample return missions.   “Given the exciting astrobiological implications raised by the Amapari Marker Band, these types of materials should be prioritized for future Curiosity chemistry analysis or for returning samples from Mars' Jezero Crater, should the opportunity arise,” Gasda said.Paper: Amapari Marker Band Metal-Enrichments: Potential Mechanisms and Implications for Surface and Subsurface Water and Weathering in Gale crater. Journal of Geophysical Research: Planets. DOI 10.1029/2025JE009153Funding: This work was funded by NASA’s Mars Exploration Program ChemCam.LA-UR-26-23031
[H5] Contact
Media Relations | media_relations@lanl.gov
[H5] Related Topics
Science, Technology & Engineering | Space
[H2] More Stories
All News
[IMG: 2026-05-21]
[H3] Data-driven modeling captures particle motion in turbulence
Machine learning model tackles challenging open physics problem
[IMG: 2026-05-06]
[H3] Scientists map the shape of RNA that can shut down genes
Understanding the ‘dark matter of the genome’ could help develop therapeutic medical advances
[IMG: 2026-04-16]
[H3] Los Alamos leads research in versatile quantum computing
Innovative experiments demonstrate valuable capabilities for quantum annealing machines
[IMG: 2026-04-16]
[H3] Meet URSA: The AI agent transforming how science gets done
AI framework is built to bring AI into the heart of scientific discovery
[IMG: 2026-04-13]
[H3] Mapping Earth’s hidden hydrogen for energy dominance
A recent study examines the vast potential of subsurface hydrogen
[IMG: 2026-04-09]
[H3] Researchers show some quantum learning models are classically simulable
Fix for quantum ‘curse of dimensionality’ may mitigate advantage versus classical computing
[H4] Subscribe to our Newsletter
Sign up to receive the latest news and feature stories from Los Alamos National LaboratorySIGN UP

April 16, 2026
[H1] Meet URSA: The AI agent transforming how science gets done
[H2] AI framework is built to bring AI into the heart of scientific discovery
What if scientists could work alongside an AI collaborator that not only understands complex research goals but helps design and carry out experiments to achieve them?That's the vision behind URSA — the Universal Research and Scientific Agent. The agentic open-source AI software package was developed at Los Alamos National Laboratory.URSA is built to bring artificial intelligence into the heart of scientific discovery — acting as a team of specialized AI agents that can brainstorm hypotheses, plan experiments, run simulations and analyze results — all while learning and adapting along the way. In early demonstrations, URSA showed its potential in challenging domains like radiation-hydrodynamics, navigating intricate design spaces to find optimal solutions faster than ever before. By bridging human intuition with machine precision, URSA is a bold step toward a future where scientists and AI work side by side to accelerate innovation across the Lab.
[H3] Pushing the frontiers of fundamental AI
URSA is not just helping scientists — it is helping to redefine what artificial intelligence can do. At its core, URSA introduces a modular, feedback-driven agent architecture that breaks away from traditional linear AI workflows. Instead of moving through fixed stages of task execution, URSA's agents operate in dynamic, nested loops of reasoning, planning and verification, adjusting their strategies based on intermediate results. This adaptability allows URSA to handle the uncertainty and complexity inherent in real scientific inquiry.
[IMG: 2026-04-16-small]
Another key innovation is how URSA grounds large language models in the physical world. By integrating with real simulation tools and experimental data, the system does not just generate text — it reasons with equations, physical models and domain knowledge. This connection to real-world physics allows URSA to engage with simulations that reflect the actual laws of nature, creating a richer and more trustworthy form of machine reasoning.To measure progress, the URSA team has developed a new benchmark framework to evaluate how well the system performs compared to established methods like Bayesian optimization. Early results show that URSA's "agentic" approach — where specialized AI agents collaborate and adapt — can lead to faster, more efficient and more accurate decision-making in complex scientific environments.
[H3] Addressing the Lab's most critical mission challenges
URSA's design aligns closely with the Lab's mission to tackle some of the most complex scientific challenges in the world. Many of these challenges — such as those in inertial confinement fusion, advanced materials or national security — depend on massive simulations and expert analysis that are both time-consuming and computationally expensive.In early applications, URSA's prototype has demonstrated the ability to accelerate these workflows. For example, in ICF research, exploring the design space for optimal configurations traditionally requires running thousands of simulations — each one resource-intensive and costly. URSA streamlines this process by intelligently selecting and evaluating candidate designs, significantly reducing the number of runs needed to identify promising results.Beyond fusion, URSA's agent-based framework could enhance simulation-guided discovery across multiple mission areas, from materials and manufacturing to stockpile modernization. By automating parts of hypothesis testing, data interpretation and optimization, URSA helps scientists extract deeper insights from supercomputing resources — not by replacing human expertise, but by amplifying it.
[H3] Looking ahead: Building the next generation of scientific AI
In the future, several avenues of research will further enhance URSA's capabilities. Ongoing research will focus on making the system more robust and reliable, particularly in managing errors or "hallucinations" that can occur when AI agents misinterpret data or miscommunicate with external tools. Improving these safeguards will be crucial for applying URSA in high-stakes environments where precision and trustworthiness are paramount.Another key direction involves scaling URSA to operate across multiple domains simultaneously, enabling teams of AI agents to collaborate across chemistry, physics, materials science and beyond. The integration of human-in-the-loop interaction is also a top priority — allowing domain experts to guide, correct and refine URSA's reasoning in real time.Together, these developments are bringing URSA closer to a new model of scientific discovery — one where humans and AI collaborate seamlessly to accelerate understanding, innovation and mission impact across the Lab.LA-UR-26-22429
[H5] Contact
Media Relations | media_relations@lanl.gov
[H5] Related Topics
Artificial Intelligence | Science, Technology & Engineering
[H2] More Stories
All News
[IMG: 2026-05-21]
[H3] Data-driven modeling captures particle motion in turbulence
Machine learning model tackles challenging open physics problem
[IMG: 2026-05-06]
[H3] Scientists map the shape of RNA that can shut down genes
Understanding the ‘dark matter of the genome’ could help develop therapeutic medical advances
[IMG: 2026-04-21]
[H3] NASA’s Curiosity Rover finds more evidence of ancient lakes on Mars
The findings shed new light on the potential for past life
[IMG: 2026-04-16]
[H3] Los Alamos leads research in versatile quantum computing
Innovative experiments demonstrate valuable capabilities for quantum annealing machines
[IMG: 2026-04-13]
[H3] Mapping Earth’s hidden hydrogen for energy dominance
A recent study examines the vast potential of subsurface hydrogen
[IMG: 2026-04-09]
[H3] Researchers show some quantum learning models are classically simulable
Fix for quantum ‘curse of dimensionality’ may mitigate advantage versus classical computing
[H4] Subscribe to our Newsletter
Sign up to receive the latest news and feature stories from Los Alamos National LaboratorySIGN UP