Agent RL

Agent RL is the reinforcement-learning and rollout problem that appears when a model is trained or adapted inside an Agent Harness rather than inside a narrow prompt-answer loop. In 138. 对罗福莉3.5小时访谈：AI范式已然巨变！OpenClaw、Agent范式很吃后训练、卡的分配、组织平权, Luo Fuli / 罗福莉 says agent-era RL infrastructure has to handle agent frameworks, GPU and CPU resources, storage, fault tolerance, compatibility, and train-inference mismatch.

The source treats Agent RL as harder and messier than ordinary post-training because the environment is not just the model inference engine. Tool use, external state, long-running tasks, memory files, simulated users, framework interruptions, and heterogeneous resources all become part of the training loop.

Key Claims

• Agent RL needs rollout infrastructure that can execute multi-step tasks through tools and frameworks, not only sample text completions.
• The environment may be fuzzy, interruptible, and inconsistent across training and deployment.
• Successful Agent RL depends on AI Verification and AI Coding Verification because weak evaluations can reward shallow completion or hidden failure.
• Infrastructure must support heterogeneous resources, including GPU inference, CPU work, storage, service calls, timeouts, and recovery after partial failure.
• Agent RL is linked to Model Harness Co-Evolution: as the model changes, the framework, reward design, and evaluation tasks may also need to change.

Connections

• Agent Post-Training — broader training frame that includes Agent RL.
• Open Claw, Open Cloud, and Agent Harness — framework and environment layer.
• Memo VR, Xiaomi, and Luo Fuli / 罗福莉 — source model-team context.
• Training Compute Allocation — compute pressure created by more parallel experiments and rollout demand.
• Multi-Agent Collaboration, ML Coding, and Long-Horizon AI — task classes where agent rollouts become useful and hard to evaluate.