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

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.

How successfully -- and efficiently! -- can agents carry out long-horizon tasks on the web? We built a benchmark of ~200 multi-site tasks, based on people's real browsing history. Many of them take hours to solve. Paper: odysseys-website.pages.dev Led by

and

Also at #ICLR2026: a new benchmark for coding agents that implement and run experiments from papers. Masking regions of code gives us a knob to control difficulty of the task (still verifiable!) Paper: arxiv.org/abs/2506.19724 Work with

, Alex Wilf, and

This morning (Fri) at #ICLR2026, check out Andy's work on ConflictScope: determining how an LLM prioritizes between a set of user-provided values, by generating scenarios where the values are in conflict. P4-#4105