lasgroup/SDPO

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1126 stars · 129 forks observed · 2026-10-20

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

SDPO (Self-Distilled Policy Optimization) is a research library implementing a reinforcement learning framework for post-training large language models. It converts tokenized environment feedback into dense learning signals by distilling the model's own feedback-informed predictions back into the policy, without an external teacher or reward model.

Use cases

• train llms with reinforcement learning on verifiable rewards
• improve sample efficiency of rl post-training for math and code reasoning
• use rich textual feedback like runtime errors as a dense training signal
• fine-tune a policy model using self-distillation from its own successful rollouts
• accelerate test-time discovery on hard binary-reward tasks

When to choose

• you are doing research on RLVR or rich-feedback reinforcement learning for LLMs
• you want denser credit assignment than scalar outcome rewards provide
• you need a reference implementation of the SDPO paper

When to avoid

• you need a production-grade, supported training framework
• you lack GPU resources for LLM post-training
• you want simple supervised fine-tuning without RL

Facets

library · maturity active

llm-training reinforcement-learning machine-learning deep-learning large-language-models machine-learning reinforcement-learning artificial-intelligence python rlvr self-distillation policy-optimization reasoning research-code verifiable-rewards gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lasgroup/SDPO")