@dan_fried

Assistant prof. @LTIatCMU @SCSatCMU. Working on NLP: LLM agents, language-to-code, applied pragmatics, grounding.

 Pittsburgh, PA
dpfried.github.io/
Joined August 2013
  • Tweets1K
  • Following947
  • Followers4.9K
33Media
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!
Graham Neubig
@gneubigSep 8
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…

CMU 11-768, AI Agents: Fall 2026

CMU 11-768 is a course teaching about AI Agents, from the fundamentals of building a harness, to evaluation, training using reinforcement learning, and other...

youtube.com
2
8
75
6,014
Daniel Fried retweeted
Andy Liu@uilydnaOct 13
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…
2
5
562
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.
Andy Liu@uilydnaOct 13
LLM developers train their models to follow prosocial values, but post-training can influence model behavior in unexpected ways. In “Predicting Alignment Generalization with Value Representations”, we ask whether downstream effects of value alignment can be predicted in advance.
1
3
26
1,730
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…

Careers - Language Technologies Institute - Kenneth C. Griffin School of Computer Science -...

Career Opportunities at Carnegie Mellon University's Language Technologies Institute

lti.cmu.edu
8
1
33
10,406
Super excited Gym-Anything won the best paper award at Lifelong Agents Workshop at #COLM2026 Special thanks to @gneubig and @wellecks for their guidance throughout the project!
28
15
1
178
9,565
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!
4
32
1
200
10,226
Zora is presenting this (and her other awesome work) as an invited talk at LSEI now - Union Square 15&16! #COLM2026
Zora Wang@ZhiruoWSep 8
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
3
35
3,114
Daniel Fried retweeted
Leena Mathur
@lmathur_Oct 9
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 🤖
Conference on Language Modeling@COLM_confOct 9
Main conference done, workshops tomorrow Thanks for everyone who attended COLM this year!
3
25
1,394
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!
2
5
1
39
2,758
Daniel Fried retweeted
Atharva Naik@AtharvaRNaikOct 9
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) 🧵👇
1
8
1
27
1,080
Come see @JangLawrenceK and @kohjingyu present the Odysseys benchmark for long horizon CUAs - poster 46, Imperial Ballroom! #COLM2026 w/ @rsalakhu
3
19
2,371
Come check out Atharva's work on easy-to-hard generalization for code listing! Poster #88 in Franciscan B. #COLM2026
Atharva Naik@AtharvaRNaikOct 8
Presenting today at 11:00 am - 1:30 pm at Franciscan B, #88 (Poster Session 5). Drop by if you are interested in chatting about long-horizon agents, slop in coding, harness evolution, or using agents for AutoML/AutoResearch.
1
21
1,180
Daniel Fried retweeted
Atharva Naik@AtharvaRNaikOct 8
Presenting today at 11:00 am - 1:30 pm at Franciscan B, #88 (Poster Session 5). Drop by if you are interested in chatting about long-horizon agents, slop in coding, harness evolution, or using agents for AutoML/AutoResearch.
Atharva Naik@AtharvaRNaikSep 28
I will be at #COLM2026 to present my work on MetaLint: Easy-to-Hard Generalization for Code Linting (arxiv.org/abs/2507.11687) and evaluating slop in long-horizon coding agents (openreview.net/pdf?id=VLgFkL…). Let's chat if you are interested in self-improvement/long horizon agents!

MetaLint: Easy-to-Hard Generalization for Code Linting

Large language models excel at code generation but struggle with code linting, particularly in generalizing to unseen or evolving best practices beyond those observed during training. We introduce...

arxiv.org
3
1
11
1,556
Daniel Fried retweeted
Russ Salakhutdinov
@rsalakhuOct 7
Replying to @JangLawrenceK
@JangLawrenceK is presenting the work OSWorld: A Benchmark for Personally Intelligent Phone Agents: Paper: arxiv.org/abs/2606.09764 Code+Web: iosworld.io An interactive benchmark built around a persistent user identity spanning 26 custom iOS apps, including analogs of OpenTable, Uber, DoorDash, AirBnB, Chase. These apps contain richly interconnected data, such as messages, transactions, travel histories, social relationships, and personal preferences. #COLM2026
Lawrence Jang
@JangLawrenceKOct 7
Me and @kohjingyu will be presenting iOSWorld at #COLM2026 tomorrow (Franciscan B, Poster #81) at 11:00 AM JY has promised a free hug to anyone who can guess his date of birth, see you there😁
2
3
44
4,996
Daniel Fried retweeted
Yijia Shao@EchoShao8899Oct 7
I proposed to give this shout-out as I found @ZhiruoW is not only technically very strong, but also genuinely passionate about mentoring and helping others grow -- and she's very good at it too. 🫡
Zora Wang@ZhiruoWOct 6
Replying to @ZhiruoW @EchoShao8899
And yes I’m on the job market 🤗
1
6
35
4,140
Daniel Fried retweeted
Emmy Liu@_emliuOct 6
Honoured to receive an outstanding paper award for our work! Couldn’t have done it without all my coauthors @KaiserWhoLearns @millicent_li @wordscompute @lltjuatja @JentseHuang and my advisor @gneubig 🫡
Conference on Language Modeling@COLM_confOct 6
Congratulations to the authors of the 3 outstanding papers! arxiv.org/abs/2607.01077 arxiv.org/abs/2604.08510 arxiv.org/abs/2604.13977
14
26
5
186
12,848
I'll be at #COLM2026 starting tomorrow! Come find the following posters today, or find me at the conference to chat about all things multi-agent (esp communication/emergent language), confidence/calibration, faithfulness, beliefs, and/or life (and several faculty openings) at UT Austin! xitter.cf/joykiratsingh/status/2… xitter.cf/vaidehi_patil_/status/…
Vaidehi Patil
@vaidehi_patil_Oct 5
Excited to be presenting our work on AI Double Agents at #COLM2026 this week! @COLM_conf 📄 Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind 🗓️ October 6 | 📍Poster #75, Franciscan A | 🕐 11:00 AM PT | Poster Session 1 I'll also be giving an AdvML Rising Star Award Presentation at AdvML-Frontiers × CoTMA workshop: From Model Security to Compositional Threats in Multi-Agent AI Systems: 🎤 Unlearning, Privacy Leakage, and Adversarial Interaction: Stress-Testing Privacy in Modern LLM Systems 🗓️ October 9 | 📍Franciscan C&D, Ballroom Level | 🕐10:15-10:30 AM PT Happy to chat about AI privacy, security, safety, multi-agent systems, post-training, evals, and more. I'm also beginning my industry job search and expect to graduate at the end of Spring 2027. I would be glad to connect with those working in these areas and discuss potential opportunities.
10
39
1,520
Come see @danieljwkim present on scaling test-time compute for agentic coding at poster 126! #COLM2026
1
3
1
33
6,471
Load more