Open Models Almanac
Methodspost-trainingagentic post-training

single mention · post-training

Multi-objective reinforcement-learning reward for agent collaboration

An RL reward combining task performance, a collaboration bonus, and a latency penalty to encourage effective coordination.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See agentic post-training for the methods filed beside it.

Filed under post-training › agentic post-training