agent training - a MercedeSnape Collection

MercedeSnape 's Collections

RAG

future

kg

memory

Evolve

reasoning evaluation

agent reasoning

mas

agent training

updated about 22 hours ago

Don't Just Fine-tune the Agent, Tune the Environment

Paper • 2510.10197 • Published Oct 11 • 28

Note 从问题实例而非SFT / RL 方法post-training