ToolRL: Reward is All Tool Learning Needs
emre can PRO
emrecanacikgoz
AI & ML interests
None yet
Recent Activity
authored
a paper
about 2 months ago
TD-EVAL: Revisiting Task-Oriented Dialogue Evaluation by Combining
Turn-Level Precision with Dialogue-Level Comparisons
authored
a paper
about 2 months ago
PIPA: A Unified Evaluation Protocol for Diagnosing Interactive Planning
Agents
authored
a paper
about 2 months ago
Self-Improving LLM Agents at Test-Time
Organizations
models
18
emrecanacikgoz/Qwen2.5-7B-Instruct-ToolRL-grpo-cold
8B
•
Updated
•
50
•
3
emrecanacikgoz/lorem-sft400-only
8B
•
Updated
•
1
emrecanacikgoz/lorem-base
8B
•
Updated
•
5
emrecanacikgoz/loremppo-sft-400
8B
•
Updated
•
2
emrecanacikgoz/lorem-sft-400
8B
•
Updated
•
1
emrecanacikgoz/SMARTAgent-Mistral-Small-24B-Instruct-2501
24B
•
Updated
•
8
emrecanacikgoz/SMARTAgent-Mistral-Nemo-Instruct-2407
12B
•
Updated
•
5
•
1
emrecanacikgoz/SMARTAgent-Mistral-7B-Instruct-v0.3
7B
•
Updated
•
4
•
1
emrecanacikgoz/SMARTAgent-Llama-3.1-70B
71B
•
Updated
•
7
emrecanacikgoz/SMARTAgent-Llama-3.1-8B
8B
•
Updated
•
7
•
1