5 repos
Bingguang/FunReason-MT
FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use
8
18 commits
RuishanFang/Qwen3-4B-RODS
RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents
0
3 commits
IcyFish/Qwen3-4B-EnvTuning
Qwen3-4B-EnvTuning
2 commits
IcyFish/Qwen3-4B-EnvTuning-Base
Qwen3-4B-EnvTuning-Base
From Failure to Mastery: Generating Hard Samples for Tool-use Agents
80
29 commits