CMU Releases AI Agents Course 11-768 with 9 Lectures Online

If unified training holds at scale, training pipelines collapse into data-mixing and scheduling decisions rather than separate stage engineering. Practitioners running continual or multi-objective training pipelines can treat it as an experimental recipe: the paper's clearest win is retaining coding ability after math RL, where staged training degraded. Anyone benchmarking against staged pipelines should note the 124M and 0.76B scale of the evidence.

elvis@omarsar0Source

The lecture distils hard-won engineering lessons, including a Token-In-Token-Out design mistake that destabilised industry-wide training, and argues that the architecture endgame is everything-as-a-service plus online RL. Engineers building RL training loops or agentic RL infrastructure can use the free slides and videos to benchmark their own system design against CMU's framework. All materials are openly accessible online, so availability is not region-restricted.

shao__meng@shao__mengSource

The research reveals a critical gap in AI agent safety monitoring where most policy violations cannot be proven from current logs, leaving users with little recourse when agents misbehave. Developers should design agents with machine-readable logs for all permissions and risky actions, as structured records could dramatically improve verifiable agent insurance systems that use blockchain deposits and automated verification.

rohanpaul_ai@rohanpaul_aiSource

The counterintuitive result is that a 4B model outperforms its 35B teacher on this editing task, suggesting harness optimisation is a better fit for small specialised models than raw capability. Builders running agent pipelines can delegate harness tuning to such an editor instead of hand-adjusting tool calls and context, iterating over several rounds per task for best results.

rohanpaul_ai@rohanpaul_aiSource

This course material reveals the critical system engineering challenges in combining training and inference engines for LLM agents, a problem often overlooked in academic papers. Developers building RL systems can implement the specific optimization techniques like Prefix Sharing and R3 to achieve up to 9.43× compression in multi-round rollouts, significantly improving efficiency for real-world deployments.

shao__meng@shao__mengSource