Add Reward Function

async def custom_rm(args, sample):
    return float_reward_or_reward_dict

async def custom_rm(args, samples):
    return list_of_rewards

If using group mode, return one reward per sample in input order.

Step 3: Keep Reward Type Consistent

• Return scalar numeric rewards unless your pipeline explicitly uses keyed rewards.
• If using reward dicts, ensure downstream reward_key / eval_reward_key is configured.
• Keep exceptions explicit for invalid metadata instead of silently returning zeros.

Step 4: Optional Reward Post-Processing

To customize normalization/shaping before advantage computation, add:

def post_process_rewards(args, samples):
    # return (raw_rewards, processed_rewards)
    ...

Wire with:

--custom-reward-post-process-path <module>.post_process_rewards

This hook is consumed in slime/ray/rollout.py.

Step 5: Wire and Validate

Use:

--custom-rm-path slime.rollout.rm_hub.<your_rm>.custom_rm

Common Mistakes

• Returning wrong output shape in group mode
• Mixing scalar rewards and reward dicts without reward_key config
• Doing blocking network calls without async handling
• Forgetting to validate reward behavior on truncated/failed samples

Reference Locations

• Reward dispatch: slime/rollout/rm_hub/__init__.py
• Reward post-process hook: slime/ray/rollout.py
• Customization docs: docs/en/get_started/customization.md