Daniel Fried

@dan_fried

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

Pittsburgh, PA

dpfried.github.io

Replies Reposts Media

Daniel Fried
@dan_fried
Sep 9
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,
Graham Neubig
@gneubig
Sep 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=…
2
Daniel Fried
@dan_fried
Sep 9
So much of working with agents today is iterative correction: co-editing outputs, nudging, re-explaining. Wouldn’t it be great if the agents learned directly from these interactions? Zora led this work on agents that adapt from human collaboration quickly (<20 interactions!)
Zora Wang
@ZhiruoW
Sep 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: 📈
GIF
1
Daniel Fried
@dan_fried
Sep 8
Super interesting (and timely!) work on how language evolves among LLM agents. It’s cool to see ideas from cultural transmission & emergent communication brought to multi-agent LLMs. Understanding these dynamics seems increasingly important for overseeing these systems.
Elias Stengel-Eskin
@EliasEskin
Sep 3
When do LLM agents develop new languages that we can’t understand? Lots of recent news about this, based mostly on anecdata from a single run. We study language emergence more rigorously, finding key factors like LLM strength, access to scratchpad messages, and pressure for
1
Daniel Fried
@dan_fried
Jul 2
We're creating a new course on AI Agents at CMU this Fall! We’re aiming to give students hands-on experience: from building agentic harnesses and evals to training with RL. Check out our course site for the full schedule: cmu-agents.com
Graham Neubig
@gneubig
Jul 2
This Fall at CMU we're teaching a new course on AI Agents! The goal is that you learn how to create a scaffold, build evals, and train an agentic LLM using RL. We'll try to balance theory and practice, and introduce modern frameworks and best practices.
8
Daniel Fried
@dan_fried
Jun 3
New work: a simple and general multi-agent computer use framework. It uses a manager to plan and re-plan by creating a task DAG, with subagents for parallel execution. It improves success rate across benchmarks, and substantially improves efficiency on long-horizon tasks.
00:00
Jing Yu Koh
@kohjingyu
Jun 3
00:23
Computer use agents are slow and brittle. The fix isn’t just stronger models, but also deploying them as multi-agent systems. MACU is a general Multi-Agent Computer Use framework that consistently lifts success rates by 3.4-25.5% and is up to 1.5x faster on long-horizon tasks.🧵
2