Pinned Tweet
We're releasing the videos for our AI agents course!
So far, we've covered tool use, context management, skills and memory, and planning.
Coming up in the next several weeks are domains (coding, GUI, deep research), and training methods (SFT, RL). Later on: frameworks, safety, interaction, and search!
We started to post videos for CMU 11-768, AI Agents!
All of the videos will be posted to this playlist, so please bookmark/follow it if you want to be notified of new ones! I'll also try to post them on this thread too.
youtube.com/playlist?list=PL…
Daniel Fried retweeted
So honored and grateful to receive the Best Resource Paper award 🏅 for this work at #EMNLP26!! Thank you @emnlpmeeting for the recognition 🥰
Huge shoutout to all my amazing collaborators: Jena D. Hwang, @elisazmq_zheng, Jenna Godsey, @hyunw_kim,
@valentina__py, @_jennhu, and especially to my most amazing and supportive advisor @MaartenSap 🎊
🚨New #EMNLP2026 paper! 🚨
Have you ever asked AI systems to do something, gotten an answer only to realize later that you’d asked the wrong question? You’re not alone!
Introducing XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions?
Spoiler alert:
🤖 LLMs only focus on what’s asked
👩🏫 Human experts answer what the asker actually needs
Daniel Fried retweeted
🚨New #EMNLP2026 paper! 🚨
Have you ever asked AI systems to do something, gotten an answer only to realize later that you’d asked the wrong question? You’re not alone!
Introducing XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions?
Spoiler alert:
🤖 LLMs only focus on what’s asked
👩🏫 Human experts answer what the asker actually needs
Daniel Fried retweeted
New preprint confirming, yes, some recent frontier models have started writing with a bunch of psycholinguistically difficult features. We say what they are (denominal verbs, inanimate subjects) and hypothesize it’s from optimizing for something other than communication.
Daniel Fried retweeted
No one changes the world alone
Introducing Ampersand - the first model built for us. Ampersand is a collaborator trained to help people achieve their individual and collective goals. In multi-month simulations, users collaborating with Ampersand accomplished more than with Fable and other frontier models
Available to everyone through our API
Daniel Fried retweeted
The UT comp ling faculty (@jessyjli, @kanishkamisra, @kmahowald & myself) are looking for PhD students to join us! sites.utexas.edu/compling/ 🤘
We are an interdisciplinary group with interests across linguistics, cogsci and NLP. Apply by 12/1: liberalarts.utexas.edu/lingu…
Daniel Fried retweeted
Just arrived in Michigan and enjoying the beautiful fall colors 🍂
I'm giving a Rising Star talk at the AI symposium about "Building Adaptive AI Agents for Humans", tomorrow at 10:30. Excited to meet everyone!
⏰ Happening TOMORROW!
The 2026 #MichiganAI Symposium brings together researchers, industry leaders & students to explore foundational models & their impact on academia, industry and society.
🎤 Keynotes, talks, posters & more, join us at @UMichCSE!
ai.engin.umich.edu/events/20…
Daniel Fried retweeted
Glad to see more work building on our previous mapping effort (arxiv.org/abs/2603.01203) to reveal the distributional gap between AI benchmarks and human work.
Surprised to see this gap remains 10 months after our study was released. Let’s build more useful benchmarks!
Mercor Research mapped AI benchmarks to actual US jobs.
Only 208 of 923 occupations in the US economy are represented by existing AI benchmarks. 90% of hours worked in the US aren't covered well by a relevant AI benchmark.
Today, we’re releasing the 𝗕𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸 𝗠𝗮𝗽 𝗼𝗳 𝘁𝗵𝗲 𝗨𝗦 𝗘𝗰𝗼𝗻𝗼𝗺𝘆, an interactive breakdown of which economic tasks are covered by AI benchmarks.
Benchmarks are how we measure AI’s progress and anticipate its impact on real work. They’re crucial to understand which jobs AI can automate, where the biggest gaps are, and how those capabilities are changing over time.
The Benchmark Map is our first step toward building a resource that makes it easier to answer: 𝘋𝘰𝘦𝘴 𝘵𝘩𝘪𝘴 𝘈𝘐 𝘮𝘰𝘥𝘦𝘭 𝘸𝘰𝘳𝘬 𝘧𝘰𝘳 𝘮𝘺 𝘰𝘤𝘤𝘶𝘱𝘢𝘵𝘪𝘰𝘯?
Explore it here: mercor.com/research/labor-in…
Daniel Fried retweeted
I'm currently on the job market for industry roles!!
I'm Yiqing Xie, a PhD student at Carnegie Mellon University working with Carolyn Rosé and Daniel Fried @dan_fried.
My work mainly focuses on agentic training, coding agents, factuality and trustworthiness, and general training data construction.
If your team is hiring (or you know someone who is), feel free to DM me and I'm super happy to chat!!
My website: yiqingxyq.github.io/;
and CV: yiqingxyq.github.io/assets/p…
Daniel Fried retweeted
Thanks to my collaborators @bhatia_mehar @karstanczak @MonaDiab77 @VeredShwartz @dan_fried for their support in making this work possible!
Project Page: andyjliu.github.io/valuegene…
Paper: arxiv.org/abs/2610.12410
Code and data: github.com/andyjliu/value-ge…
Andy led this work predicting ripple effects when training LLMs on particular values, across 66 values. Model activations are much more predictive than value descriptions! A step toward predicting the side effects of alignment training.
Daniel Fried retweeted
The LTI is hiring for teaching track and tenure track faculty positions to start in the Fall 2027 semester. See our Careers page for full details and access to the application portal. Note: Teaching Track applicants are encouraged to apply by October 23!
lti.cmu.edu/careers/index.ht…
Daniel Fried retweeted
Second piece of news, I’m looking to recruit multiple PhD students to work on human-centered AI/alignment/LLM social reasoning this cycle @UTiSchool
While I’m sadly missing #COLM2026 I'll be heading to #EMNLP2026 🇭🇺
Whether you'll be there or not, reach out if you're interested!
Zora is presenting this (and her other awesome work) as an invited talk at LSEI now - Union Square 15&16! #COLM2026
Agents trained on population-scale data can do a lot of things.
But ask a professional to stake their reputation on an AI-generated artifact? “Pretty good” isn’t good enough.
We introduce TAHI: a Test-time Adaptive agent framework through Human-agent Interaction. Featuring:
📈 Test-time adaptation via context (memory, skills) and weight training
⚡ Efficient adaptation to individual expertise within tens of tasks
✔️ Creating comprehensive rubrics for “non-verifiable” tasks
🔍 Analysis of shared community guidelines vs. personalized tacit expertise
Daniel Fried retweeted
Our #COLM2026 workshop on Learning from Situated and Embodied Interaction is starting soon!
Join us today in Union Sq 15&16 on the 4th floor to hear talks from Noam Brown @polynoamial, Been Kim @_beenkim, Heng Ji @hengjinlp, Diyi Yang @Diyi_Yang , and Zora Wang @ZhiruoW!
We will also have a group brainstorming session in the afternoon 🤖
Daniel Fried retweeted
I will be presenting Gym-Anything oral at #COLM2026 workshop on lifelong learning agents.
🗓 12pm at Imperial Ballroom 6
If you are interested in computer use agents or how to make rl environments, do check it out!
Daniel Fried retweeted
Tired of AI slop and spaghetti code? We study how to measure and reduce slop in long-horizon coding agents in this work, which will be presented at the #COLM Workshop on Agent Behavior (October 9, 10 - 11:30 AM at Continental Ballroom) 🧵👇
Come see @JangLawrenceK and @kohjingyu present the Odysseys benchmark for long horizon CUAs - poster 46, Imperial Ballroom! #COLM2026 w/ @rsalakhu
