WEBVTT
Kind: captions
Language: en-US
00:00:00.000 --> 00:00:00.142
[MUSIC]
00:00:00.142 --> 00:00:04.160
SOWBHAGYA SURESH: Hi, I’m Sowbhagya Suresh.
Welcome to Microsoft Research Focus.
00:00:04.160 --> 00:00:08.400
You've probably read our newsletter. And now
you can get highlights from across the research
00:00:08.400 --> 00:00:14.400
community at Microsoft here, on YouTube, and
major podcast platforms. Whether you read,
00:00:14.400 --> 00:00:19.760
watch, or listen to it, Research Focus is
your source for research news at Microsoft.
00:00:19.760 --> 00:00:25.280
Coming up in this edition: what everyday
AI use reveals about the way we work;
00:00:25.280 --> 00:00:30.480
how a new AI model could help scientists
better understand proteins; a new approach
00:00:30.480 --> 00:00:39.920
to improving weather forecasts weeks in
advance; and more. So here's what's new.
00:00:44.800 --> 00:00:48.466
More and more, AI agents are
handling tasks that are complex.
00:00:48.466 --> 00:00:48.480
[MUSIC FADES]
00:00:48.480 --> 00:00:53.920
Tasks that require multiple steps, decisions,
and interactions with external tools. But how
00:00:53.920 --> 00:00:58.080
can we count on AI agents to do the work
if their ability to adjust when things
00:00:58.080 --> 00:01:03.280
go wrong may require a lot of resources
with no guarantees of a better result?
00:01:03.280 --> 00:01:08.800
A new self-improving framework called ForkPilot
learns when it's worth revisiting earlier
00:01:08.800 --> 00:01:14.080
decisions to find a different approach and
adapts its strategy based on new outcomes.
00:01:14.080 --> 00:01:19.200
Tested across six benchmarks and leading
AI models, ForkPilot measures up to the
00:01:19.200 --> 00:01:24.640
best existing methods while reducing
AI processing demands by up to 59%.
00:01:24.640 --> 00:01:30.080
These results suggest that AI agents can solve
complex problems more reliably and efficiently,
00:01:30.080 --> 00:01:35.341
making them more practical and
cost-effective to deploy at scale.
00:01:35.341 --> 00:01:35.360
[TRANSITION MUSIC]
00:01:35.360 --> 00:01:41.440
Coding agents execute user queries by reasoning
about, editing, and running code. Understanding
00:01:41.440 --> 00:01:47.280
why these agents fail is critical if we want to
build more capable and reliable coding agents.
00:01:47.280 --> 00:01:52.000
Unfortunately, existing benchmarks
often make it difficult to identify
00:01:52.000 --> 00:01:54.800
which factors contribute to success or failure.
00:01:54.800 --> 00:01:58.880
CABRA is a framework for generating
coding challenges from scratch. It
00:01:58.880 --> 00:02:02.960
lets researchers increase complexity
in a controlled way and pinpoints
00:02:02.960 --> 00:02:05.520
the skills that are most difficult for agents.
00:02:05.520 --> 00:02:10.800
Across thousands of generated challenges, the
researchers found that agents often overcame
00:02:10.800 --> 00:02:16.480
coding problems by using tools. Yet the agents
still struggled when they needed to understand
00:02:16.480 --> 00:02:22.320
unfamiliar codebases. The findings suggest that
understanding existing code, rather than modifying
00:02:22.320 --> 00:02:29.341
it, remains one of the biggest obstacles
to developing more effective coding agents.
00:02:29.341 --> 00:02:29.360
[TRANSITION MUSIC]
00:02:29.360 --> 00:02:33.840
Computer-use agents are AI systems that
are designed to complete tasks that
00:02:33.840 --> 00:02:39.680
require clicking and typing. They can fill in
forms, process requests, and navigate websites.
00:02:39.680 --> 00:02:44.240
To do this effectively, they need to learn
the procedures that people use to get work
00:02:44.240 --> 00:02:48.960
done. User activity logs can offer a way
to capture this knowledge. But activity
00:02:48.960 --> 00:02:54.320
logs typically don't record the intent
behind each action and often combine tasks.
00:02:54.320 --> 00:02:58.720
The new framework TeleTune learns
reusable skills and workflows from
00:02:58.720 --> 00:03:04.640
these logs. It also infers the task goals
associated with the sequences of actions.
00:03:04.640 --> 00:03:09.120
In evaluations across software and
browser tasks, TeleTune outperformed
00:03:09.120 --> 00:03:14.880
existing approaches. By learning from existing
activity, TeleTune offers a scalable way to
00:03:14.880 --> 00:03:22.701
help AI agents adapt to unfamiliar software
and carry out complex, multi-step workflows
00:03:22.701 --> 00:03:22.720
[TRANSITION MUSIC]
00:03:22.720 --> 00:03:27.520
Workers across industries may appear to
be using AI in surprisingly similar ways,
00:03:27.520 --> 00:03:30.640
but a closer look reveals a different story.
00:03:30.640 --> 00:03:35.520
Microsoft researchers analyzed aggregated
Copilot Chat activity across a broad range
00:03:35.520 --> 00:03:40.000
of customer categories and found that
editing documents led all classified
00:03:40.000 --> 00:03:42.400
activities, accounting for more than 20 percent.
00:03:42.400 --> 00:03:47.120
But when researchers set aside the 20 most
common activities, differences between
00:03:47.120 --> 00:03:52.000
customer categories became substantially
more pronounced. The most common uses of
00:03:52.000 --> 00:03:57.360
AI may be hiding important differences in how
organizations use it for more specialized work.
00:03:57.360 --> 00:04:02.240
For business leaders, the takeaway is clear:
don’t assume you have the same AI needs as
00:04:02.240 --> 00:04:07.360
others in your industry. Finding the right
opportunities means looking beyond usage
00:04:07.360 --> 00:04:15.261
statistics to understand what employees actually
do, how they work, and what outcomes matter most.
00:04:15.261 --> 00:04:15.280
[TRANSITION MUSIC]
00:04:15.280 --> 00:04:20.320
A new study shows how Shiksha Copilot—a
human-in-the-loop AI tool—could transform
00:04:20.320 --> 00:04:23.040
teacher workflows in Global South classrooms.
00:04:23.040 --> 00:04:26.480
The study in low-resource schools
in India found the tool reduced
00:04:26.480 --> 00:04:31.280
the time teachers spent on bilingual
lesson planning and bureaucracy. That
00:04:31.280 --> 00:04:35.040
gave them more time to craft more
engaging classroom activities.
00:04:35.040 --> 00:04:40.480
More than a thousand teachers participated, and
many reported reduced stress levels and a positive
00:04:40.480 --> 00:04:45.840
impression of how AI can help them. These teachers
actively engaged with Shiksha Copilot, using their
00:04:45.840 --> 00:04:51.360
professional expertise to adapt and repurpose
materials to suit their own classrooms.
00:04:51.360 --> 00:04:52.720
[TRANSITION MUSIC]
00:04:52.720 --> 00:04:59.200
Ten-day weather forecasts have become remarkably
dependable. But what about the weeks that follow?
00:04:59.200 --> 00:05:03.360
The two-to-six-week window remains a
major challenge for forecasting models,
00:05:03.360 --> 00:05:07.440
which is a problem. That’s when a wide
range of critical decisions get made
00:05:07.440 --> 00:05:11.760
related to farming, managing wildfires,
and preparing for extreme weather.
00:05:11.760 --> 00:05:16.720
A new machine-learning framework called
Probabilistic Bias Correction, or PBC, is
00:05:16.720 --> 00:05:22.000
helping close that gap. PBC learns from a weather
model's past mistakes and helps correct them.
00:05:22.000 --> 00:05:24.000
And the early results are promising.
00:05:24.000 --> 00:05:27.840
PBC took top honors in a global
competition focused on improving
00:05:27.840 --> 00:05:31.440
extended-range forecasting. It's
also being deployed in Kenya,
00:05:31.440 --> 00:05:35.040
where it's helping improve critical
monsoon forecasts for farmers.
00:05:35.040 --> 00:05:36.880
This development could help make weather
00:05:36.880 --> 00:05:41.440
predictions more useful across
a broad range of applications.
00:05:42.800 --> 00:05:43.600
[TRANSITION MUSIC]
00:05:43.600 --> 00:05:47.200
BioEmu2, a new foundation model for
understanding biomolecular structure,
00:05:47.200 --> 00:05:50.880
dynamics, and function, is now
available in public preview.
00:05:50.880 --> 00:05:56.320
Developed by the Microsoft Research AI for
Science team, BioEmu2 builds on Biomolecular
00:05:56.320 --> 00:06:01.920
Emulator, a deep-learning model designed to help
scientists better understand how proteins work.
00:06:01.920 --> 00:06:06.240
That understanding could have important
implications for medicine. By learning
00:06:06.240 --> 00:06:11.600
more about how proteins function, scientists
could move closer to developing more effective
00:06:11.600 --> 00:06:17.040
medications that enhance beneficial protein
activity or prevent proteins from causing harm.
00:06:17.040 --> 00:06:22.840
Go to the BioEmu2 Microsoft Research GitHub
repository to explore the model and learn more.
00:06:22.840 --> 00:06:23.760
[MUSIC]
00:06:23.760 --> 00:06:25.520
And that’s your Research Focus.
00:06:25.520 --> 00:06:28.800
From more capable AI agents
to better weather forecasting,
00:06:28.800 --> 00:06:32.640
these are just a few of the developments
researchers are exploring at Microsoft.
00:06:32.640 --> 00:06:36.720
Want to learn more and stay connected?
Explore the latest research, discover
00:06:36.720 --> 00:06:40.720
the people behind it, and keep tabs
on the ideas shaping what's next by
00:06:40.720 --> 00:06:43.600
following Microsoft Research
on major social platforms.
00:06:43.600 --> 00:06:45.760
I'm
Sowbhagya Suresh. Thanks so much for tuning
00:06:45.760 --> 00:06:51.520
in. We’ll see you in the next
Microsoft Research Focus.
00:06:51.520 --> 00:06:52.362
[MUSIC FADES]
Kind: captions
Language: en-US
00:00:00.000 --> 00:00:00.142
[MUSIC]
00:00:00.142 --> 00:00:04.160
SOWBHAGYA SURESH: Hi, I’m Sowbhagya Suresh.
Welcome to Microsoft Research Focus.
00:00:04.160 --> 00:00:08.400
You've probably read our newsletter. And now
you can get highlights from across the research
00:00:08.400 --> 00:00:14.400
community at Microsoft here, on YouTube, and
major podcast platforms. Whether you read,
00:00:14.400 --> 00:00:19.760
watch, or listen to it, Research Focus is
your source for research news at Microsoft.
00:00:19.760 --> 00:00:25.280
Coming up in this edition: what everyday
AI use reveals about the way we work;
00:00:25.280 --> 00:00:30.480
how a new AI model could help scientists
better understand proteins; a new approach
00:00:30.480 --> 00:00:39.920
to improving weather forecasts weeks in
advance; and more. So here's what's new.
00:00:44.800 --> 00:00:48.466
More and more, AI agents are
handling tasks that are complex.
00:00:48.466 --> 00:00:48.480
[MUSIC FADES]
00:00:48.480 --> 00:00:53.920
Tasks that require multiple steps, decisions,
and interactions with external tools. But how
00:00:53.920 --> 00:00:58.080
can we count on AI agents to do the work
if their ability to adjust when things
00:00:58.080 --> 00:01:03.280
go wrong may require a lot of resources
with no guarantees of a better result?
00:01:03.280 --> 00:01:08.800
A new self-improving framework called ForkPilot
learns when it's worth revisiting earlier
00:01:08.800 --> 00:01:14.080
decisions to find a different approach and
adapts its strategy based on new outcomes.
00:01:14.080 --> 00:01:19.200
Tested across six benchmarks and leading
AI models, ForkPilot measures up to the
00:01:19.200 --> 00:01:24.640
best existing methods while reducing
AI processing demands by up to 59%.
00:01:24.640 --> 00:01:30.080
These results suggest that AI agents can solve
complex problems more reliably and efficiently,
00:01:30.080 --> 00:01:35.341
making them more practical and
cost-effective to deploy at scale.
00:01:35.341 --> 00:01:35.360
[TRANSITION MUSIC]
00:01:35.360 --> 00:01:41.440
Coding agents execute user queries by reasoning
about, editing, and running code. Understanding
00:01:41.440 --> 00:01:47.280
why these agents fail is critical if we want to
build more capable and reliable coding agents.
00:01:47.280 --> 00:01:52.000
Unfortunately, existing benchmarks
often make it difficult to identify
00:01:52.000 --> 00:01:54.800
which factors contribute to success or failure.
00:01:54.800 --> 00:01:58.880
CABRA is a framework for generating
coding challenges from scratch. It
00:01:58.880 --> 00:02:02.960
lets researchers increase complexity
in a controlled way and pinpoints
00:02:02.960 --> 00:02:05.520
the skills that are most difficult for agents.
00:02:05.520 --> 00:02:10.800
Across thousands of generated challenges, the
researchers found that agents often overcame
00:02:10.800 --> 00:02:16.480
coding problems by using tools. Yet the agents
still struggled when they needed to understand
00:02:16.480 --> 00:02:22.320
unfamiliar codebases. The findings suggest that
understanding existing code, rather than modifying
00:02:22.320 --> 00:02:29.341
it, remains one of the biggest obstacles
to developing more effective coding agents.
00:02:29.341 --> 00:02:29.360
[TRANSITION MUSIC]
00:02:29.360 --> 00:02:33.840
Computer-use agents are AI systems that
are designed to complete tasks that
00:02:33.840 --> 00:02:39.680
require clicking and typing. They can fill in
forms, process requests, and navigate websites.
00:02:39.680 --> 00:02:44.240
To do this effectively, they need to learn
the procedures that people use to get work
00:02:44.240 --> 00:02:48.960
done. User activity logs can offer a way
to capture this knowledge. But activity
00:02:48.960 --> 00:02:54.320
logs typically don't record the intent
behind each action and often combine tasks.
00:02:54.320 --> 00:02:58.720
The new framework TeleTune learns
reusable skills and workflows from
00:02:58.720 --> 00:03:04.640
these logs. It also infers the task goals
associated with the sequences of actions.
00:03:04.640 --> 00:03:09.120
In evaluations across software and
browser tasks, TeleTune outperformed
00:03:09.120 --> 00:03:14.880
existing approaches. By learning from existing
activity, TeleTune offers a scalable way to
00:03:14.880 --> 00:03:22.701
help AI agents adapt to unfamiliar software
and carry out complex, multi-step workflows
00:03:22.701 --> 00:03:22.720
[TRANSITION MUSIC]
00:03:22.720 --> 00:03:27.520
Workers across industries may appear to
be using AI in surprisingly similar ways,
00:03:27.520 --> 00:03:30.640
but a closer look reveals a different story.
00:03:30.640 --> 00:03:35.520
Microsoft researchers analyzed aggregated
Copilot Chat activity across a broad range
00:03:35.520 --> 00:03:40.000
of customer categories and found that
editing documents led all classified
00:03:40.000 --> 00:03:42.400
activities, accounting for more than 20 percent.
00:03:42.400 --> 00:03:47.120
But when researchers set aside the 20 most
common activities, differences between
00:03:47.120 --> 00:03:52.000
customer categories became substantially
more pronounced. The most common uses of
00:03:52.000 --> 00:03:57.360
AI may be hiding important differences in how
organizations use it for more specialized work.
00:03:57.360 --> 00:04:02.240
For business leaders, the takeaway is clear:
don’t assume you have the same AI needs as
00:04:02.240 --> 00:04:07.360
others in your industry. Finding the right
opportunities means looking beyond usage
00:04:07.360 --> 00:04:15.261
statistics to understand what employees actually
do, how they work, and what outcomes matter most.
00:04:15.261 --> 00:04:15.280
[TRANSITION MUSIC]
00:04:15.280 --> 00:04:20.320
A new study shows how Shiksha Copilot—a
human-in-the-loop AI tool—could transform
00:04:20.320 --> 00:04:23.040
teacher workflows in Global South classrooms.
00:04:23.040 --> 00:04:26.480
The study in low-resource schools
in India found the tool reduced
00:04:26.480 --> 00:04:31.280
the time teachers spent on bilingual
lesson planning and bureaucracy. That
00:04:31.280 --> 00:04:35.040
gave them more time to craft more
engaging classroom activities.
00:04:35.040 --> 00:04:40.480
More than a thousand teachers participated, and
many reported reduced stress levels and a positive
00:04:40.480 --> 00:04:45.840
impression of how AI can help them. These teachers
actively engaged with Shiksha Copilot, using their
00:04:45.840 --> 00:04:51.360
professional expertise to adapt and repurpose
materials to suit their own classrooms.
00:04:51.360 --> 00:04:52.720
[TRANSITION MUSIC]
00:04:52.720 --> 00:04:59.200
Ten-day weather forecasts have become remarkably
dependable. But what about the weeks that follow?
00:04:59.200 --> 00:05:03.360
The two-to-six-week window remains a
major challenge for forecasting models,
00:05:03.360 --> 00:05:07.440
which is a problem. That’s when a wide
range of critical decisions get made
00:05:07.440 --> 00:05:11.760
related to farming, managing wildfires,
and preparing for extreme weather.
00:05:11.760 --> 00:05:16.720
A new machine-learning framework called
Probabilistic Bias Correction, or PBC, is
00:05:16.720 --> 00:05:22.000
helping close that gap. PBC learns from a weather
model's past mistakes and helps correct them.
00:05:22.000 --> 00:05:24.000
And the early results are promising.
00:05:24.000 --> 00:05:27.840
PBC took top honors in a global
competition focused on improving
00:05:27.840 --> 00:05:31.440
extended-range forecasting. It's
also being deployed in Kenya,
00:05:31.440 --> 00:05:35.040
where it's helping improve critical
monsoon forecasts for farmers.
00:05:35.040 --> 00:05:36.880
This development could help make weather
00:05:36.880 --> 00:05:41.440
predictions more useful across
a broad range of applications.
00:05:42.800 --> 00:05:43.600
[TRANSITION MUSIC]
00:05:43.600 --> 00:05:47.200
BioEmu2, a new foundation model for
understanding biomolecular structure,
00:05:47.200 --> 00:05:50.880
dynamics, and function, is now
available in public preview.
00:05:50.880 --> 00:05:56.320
Developed by the Microsoft Research AI for
Science team, BioEmu2 builds on Biomolecular
00:05:56.320 --> 00:06:01.920
Emulator, a deep-learning model designed to help
scientists better understand how proteins work.
00:06:01.920 --> 00:06:06.240
That understanding could have important
implications for medicine. By learning
00:06:06.240 --> 00:06:11.600
more about how proteins function, scientists
could move closer to developing more effective
00:06:11.600 --> 00:06:17.040
medications that enhance beneficial protein
activity or prevent proteins from causing harm.
00:06:17.040 --> 00:06:22.840
Go to the BioEmu2 Microsoft Research GitHub
repository to explore the model and learn more.
00:06:22.840 --> 00:06:23.760
[MUSIC]
00:06:23.760 --> 00:06:25.520
And that’s your Research Focus.
00:06:25.520 --> 00:06:28.800
From more capable AI agents
to better weather forecasting,
00:06:28.800 --> 00:06:32.640
these are just a few of the developments
researchers are exploring at Microsoft.
00:06:32.640 --> 00:06:36.720
Want to learn more and stay connected?
Explore the latest research, discover
00:06:36.720 --> 00:06:40.720
the people behind it, and keep tabs
on the ideas shaping what's next by
00:06:40.720 --> 00:06:43.600
following Microsoft Research
on major social platforms.
00:06:43.600 --> 00:06:45.760
I'm
Sowbhagya Suresh. Thanks so much for tuning
00:06:45.760 --> 00:06:51.520
in. We’ll see you in the next
Microsoft Research Focus.
00:06:51.520 --> 00:06:52.362
[MUSIC FADES]
