agential-ai/agential
🔔🧠Easily experiment with popular language agents across diverse reasoning/decision-making benchmarks!
PythonMIT
Issues
- 0
[Feature Request]: MBPP for LATS
#224 opened - 0
[Feature Request]: HumanEval for LATS
#223 opened - 0
[Feature Request]: TabMWP for LATS
#222 opened - 0
[Feature Request]: SVAMP for LATS
#221 opened - 0
[Feature Request]: GSM8K for LATS
#220 opened - 0
[Feature Request]: AmbigNQ for LATS
#219 opened - 0
[Feature Request]: FEVER for LATS
#218 opened - 0
[Feature Request]: TriviaQA for LATS
#217 opened - 0
[Feature Request]: HotpotQA for LATS
#216 opened - 0
[Feature Request]: LATS
#215 opened - 0
[Feature Request]: MBPP for Self-Refine
#214 opened - 0
[Feature Request]: HumanEval for Self-Refine
#213 opened - 0
[Feature Request]: TabMWP for Self-Refine
#212 opened - 0
[Feature Request]: SVAMP for Self-Refine
#211 opened - 0
[Feature Request]: GSM8K for Self-Refine
#210 opened - 0
[Feature Request]: AmbigNQ for Self-Refine
#209 opened - 0
[Feature Request]: FEVER for Self-Refine
#208 opened - 0
[Feature Request]: TriviaQA for Self-Refine
#207 opened - 0
[Feature Request]: HotpotQA for Self-Refine
#206 opened - 0
- 0
- 0
- 0
[Feature Request]: MATH Benchmark
#190 opened - 0
[Feature Request]: Re-introduce Self-Refine
#189 opened - 0
- 0
- 0
- 0
- 0
- 0
[Feature Request]: Universal Selector
#168 opened - 0
- 0
[Feature Request]: Adding Notebooks for Demo
#165 opened - 0
[Feature Request]: Refactoring ReAct
#164 opened - 0
[Feature Request]: Refactor Self-Refine
#161 opened - 0
[Feature Request]: Benchmarks Module
#160 opened - 0
- 0
- 0
- 0
- 0
[Feature Request]: Refactor CRITIC
#141 opened - 0
- 0
- 0
[Feature Request]: AgentBench for Reflexion
#133 opened - 0
[Feature Request]: WebShop for Reflexion
#132 opened - 0
[Feature Request]: ALFWorld for Reflexion
#131 opened - 0
[Feature Request]: Reflexion
#130 opened - 0
[Feature Request]: HumanEval for Reflexion
#129 opened - 0
[Feature Request]: MBPP for Reflexion
#128 opened - 0
[Feature Request]: TabMWP for Reflexion
#127 opened - 0
[Feature Request]: SVAMP for Reflexion
#126 opened