TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
Paper
•
2510.01179
•
Published
•
25
•
3
Ziyang Luo
Ziyang
AI & ML interests
Agents, LLMs, Multimodal ML
Recent Activity
upvoted
a
paper
9 days ago
UserRL: Training Interactive User-Centric Agent via Reinforcement
Learning
upvoted
a
collection
9 days ago
GTA1
upvoted
a
collection
9 days ago
Elastic-Reasoning
Organizations
commented
a
paper
2 months ago
commented
4
papers
3 months ago
MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers
Paper
•
2508.14704
•
Published
•
43
•
10
MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers
Paper
•
2508.14704
•
Published
•
43
•
10
MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers
Paper
•
2508.14704
•
Published
•
43
•
10
MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers
Paper
•
2508.14704
•
Published
•
43
•
10
commented
a
paper
4 months ago
Add task category
#3 opened 9 months ago
by
nielsr
commented
a
paper
about 1 year ago
Dataset Size
3
#2 opened over 1 year ago
by
Kris126
Invalid shape error
3
#20 opened over 2 years ago
by
vermanic
Build chat bot
👍
2
3
#16 opened over 2 years ago
by
Hashif
tokenizer.model file missing?
3
#37 opened over 2 years ago
by
RustyRobot
wrong bos_token
3
#15 opened over 2 years ago
by
loubnabnl
Details on the method used to surpass CodeLlama
1
#14 opened over 2 years ago
by
ETN3I
Performance issues when compared to other codellama_34b finetunes
6
#11 opened over 2 years ago
by
rombodawg
Performance issues when compared to other codellama_34b finetunes
6
#11 opened over 2 years ago
by
rombodawg
Performance issues when compared to other codellama_34b finetunes
6
#11 opened over 2 years ago
by
rombodawg