[ VERIFIED_VIA_MULTI_SOURCE_INTELLIGENCE ]
[ SOURCE: https://github.com/radixark/miles ]
[ TIMESTAMP: 2026-09-04 12:00:45 ]

miles

Reinforcement learning framework for LLM and VLM post-training. Forked from slime, co-evolving with it.

01_CORE_FEATURES

02_DEEP_ANALYSIS

FeatureMilesCompetitor ACompetitor B
Type of learningReinforcementSupervisedUnsupervised
Framework originForked from slimeProprietaryOpen-source
Model supportLLM, VLMLLM onlyVLM only
Documentation availabilityBasicComprehensiveLimited
FINAL_VERDICT
WAIT

Wicked Analysis Engine Recommendation

[ SHARE ON X ]
[ EMBED_BADGE ]

Embed this verdict on your site or README.

Wicked.today verdict: WAIT view .svg
HTML
<a href="https://wicked.today/report/miles" target="_blank"><img src="https://wicked.today/badge/miles.svg" alt="Wicked.today: WAIT"></a>
Markdown
[![Wicked.today: WAIT](https://wicked.today/badge/miles.svg)](https://wicked.today/report/miles)