-
If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents
Paper • 2401.00812 • Published • 12 -
DynaSaur: Large Language Agents Beyond Predefined Actions
Paper • 2411.01747 • Published • 38 -
GAIA: a benchmark for General AI Assistants
Paper • 2311.12983 • Published • 253 -
Executable Code Actions Elicit Better LLM Agents
Paper • 2402.01030 • Published • 198
Tim Wheeler
ninetyone
·
AI & ML interests
None yet
Organizations
None yet
agents
-
If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents
Paper • 2401.00812 • Published • 12 -
DynaSaur: Large Language Agents Beyond Predefined Actions
Paper • 2411.01747 • Published • 38 -
GAIA: a benchmark for General AI Assistants
Paper • 2311.12983 • Published • 253 -
Executable Code Actions Elicit Better LLM Agents
Paper • 2402.01030 • Published • 198
models 0
None public yet
datasets 6
ninetyone/so100_training_20250103_003
SO-100 • Updated • 2 episodes • 49
ninetyone/so100_training_20250102_002
SO-100 • Updated • 2 episodes • 57 • 2
ninetyone/so100_training_20250102_001
SO-100 • Updated • 2 episodes • 38
ninetyone/so100_training_20250101_001
SO-100 • Updated • 2 episodes • 56
ninetyone/so100_training
SO-100 • Updated • 1 episodes • 43
ninetyone/so100_test
SO-100 • Updated • 1 episodes • 33