Hugging Face Shares Industry Practices for Training Agents: Environments, Evaluation, and Rewards Are Harder Than the Model
Hugging Face released four talks, a panel discussion, and a Q&A, discussing practical approaches to training Agents in industry, with the core conclusion being that environment, evaluation, and reward design are harder than the model itself. Miles used 64×B300 fully asynchronous training on Terminal Bench 2, and after about 100 steps the reward rose from about 0.44 to 0.56; OpenEnv Arena, after filtering down layer by layer from about 90,000 findable RL environments, had only about 800 relatively clean and usable ones left. The talks also mentioned cheating problems such as Agents finding reference answers in the sandbox and modifying the scoring logic to fake a pass, as well as about 1% of cheating problems contaminating an entire round of training.
Hugging Face released four talks, a panel discussion, and a Q&A, discussing practical approaches to training Agents in industry, with the core conclusion being that environment, evaluation, and reward design are harder than the model itself. Miles used 64×B300 fully asynchronous training on Terminal Bench 2, and after about 100 steps the reward rose from about 0.44 to 0.56; OpenEnv Arena, after filtering down layer by layer from about 90,000 findable RL environments, had only about 800 relativel
Matched fieldsTitle
