Issues
- 7
How to run a specific alfworld environment?
#34 opened by ai-nikolai - 10
Reproducing Alfworld Results
#35 opened by ai-nikolai - 0
Low Success Rate of Lookup Action in HotpotQA Reproduction with ReactReflectAgent
#46 opened by ShawnMenz - 5
HotpotQA oracle evaluator
#11 opened by linyongnan - 1
Using Ground Truth in Evaluator for HotpotQA
#45 opened by Skevinci - 7
- 0
Why i receive this warning
#44 opened by beishangeyu - 4
Using CodeLLAMA cause the program crash
#39 opened by allanj - 5
Can use local LLM?not openai api
#38 opened by liucheny - 3
- 0
Reproducing HotpotQA Results
#43 opened by haoyb22 - 1
Always fails to execute the action, and it responds with 'nothing happens'.
#41 opened by prettystar0203 - 1
Script for leetcode results
#29 opened by shenao-zhang - 5
About reflexion temperature(for HotpotQA)
#24 opened by pengjiao123 - 5
Can't reproduce HumanEval score
#30 opened by geekan - 5
- 0
Prompt for Llama-2-7b-chat-hf model
#37 opened by oximi123 - 5
- 1
- 0
- 4
label leaks may happen?
#27 opened by LongLiveSocialism - 0
About the action limitation on Webshop
#21 opened by zzh068 - 1
ModuleNotFoundError: No module named 'alfworld'
#22 opened by uglyghost - 0
what's the difference between COT_INSTRUCTION & COT_AGENT_REFLECT_INSTRUCTION in prompts.py
#32 opened by ShellingFord221 - 0
I'm not getting any results in the native webshop environment. Can you please help me understand what might be wrong?
#33 opened by huayicong23 - 4
About the prompt for reflection
#26 opened by Statisticss - 0
Content filtering using gpt3.5-turbo-16k
#25 opened by ZhaoyangLi-1 - 8
- 0
[Feature Request]: Gymnasium compatibility
#17 opened by elliottower - 1
- 1
How to run the code
#5 opened by Mohitraj87 - 0
Please integrate Reflexion into GPT-Engineer
#14 opened by Emasoft - 1
Add support for MultiPL-E
#4 opened by Randl - 2
"is_solved": false on all results
#2 opened by drammen94 - 1
What's the difference between these strategies
#12 opened by gjm-anban - 6
Interpreting results files
#3 opened by sachit-menon