HuatuoGPT-3: RL-Only Domain Adaptation from Base Models

arXiv:2610.05966 · cs.CL, cs.AI · Submitted 2026-10-05 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-10-05

Updated: 2026-10-05

Code: https://github.com/FreedomIntelligence/HuatuoGPT-3

Terminology

Adaptation — 1× in this paper · explained in 1 episode
Domain Adaptation — 1× in this paper · explained in 5 episodes

Sources

AlpaCare:Instruction-tuned Large Language Models for Medical Application
InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning
Domain-Adaptation through Synthetic Data: Fine-Tuning Large Language Models for German Law
ChemLLM: A Chemical Large Language Model
HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
Baichuan-M2: Scaling Medical Capability with Large Verifier System
Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making
Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance
Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models
An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
Consistency is the key to further mitigating catastrophic forgetting in continual learning
Adapting Large Language Models to Domains via Reading Comprehension
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Learning to Reason under Off-Policy Guidance
Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Related papers