noahshinn/reflexion issues and pull requests

#45 - Using Ground Truth in Evaluator for HotpotQA

Issue - State: open - Opened by Skevinci 3 months ago - 1 comment

#44 - Why i receive this warning

Issue - State: closed - Opened by beishangeyu 3 months ago

#43 - Reproducing HotpotQA Results

Issue - State: open - Opened by haoyb22 3 months ago

#42 - Inconsistencies with the humaneval dataset

Issue - State: closed - Opened by HamedTaherkhani 4 months ago - 3 comments

#41 - Always fails to execute the action, and it responds with 'nothing happens'.

Issue - State: open - Opened by prettystar0203 7 months ago - 1 comment

#40 - Potential unexpected behavior in executor (that uses the`global`)

Issue - State: open - Opened by allanj 8 months ago - 5 comments

#39 - Using CodeLLAMA cause the program crash

Issue - State: open - Opened by allanj 8 months ago - 4 comments

#38 - Can use local LLM？not openai api

Issue - State: open - Opened by liucheny 8 months ago - 5 comments

#37 - Prompt for Llama-2-7b-chat-hf model

Issue - State: open - Opened by oximi123 8 months ago

#36 - actor in webshop does not intake the memory and relfexion

Issue - State: open - Opened by yananchen1989 10 months ago - 7 comments

#35 - Reproducing Alfworld Results

Issue - State: open - Opened by ai-nikolai 10 months ago - 9 comments

#34 - How to run a specific alfworld environment?

Issue - State: open - Opened by ai-nikolai 10 months ago

#33 - I'm not getting any results in the native webshop environment. Can you please help me understand what might be wrong?

Issue - State: closed - Opened by huayicong23 12 months ago

#32 - what's the difference between COT_INSTRUCTION & COT_AGENT_REFLECT_INSTRUCTION in prompts.py

Issue - State: closed - Opened by ShellingFord221 about 1 year ago

#31 - ValueError: AlfWorld Environment [expert_plan, expert_type]

Issue - State: closed - Opened by ai-nikolai about 1 year ago - 1 comment

#30 - Can't reproduce HumanEval score

Issue - State: closed - Opened by geekan about 1 year ago - 5 comments

#29 - Script for leetcode results

Issue - State: open - Opened by shenao-zhang about 1 year ago - 1 comment

#28 - Clarification on ReflexionStrategy Implementation

Issue - State: closed - Opened by zapqqqwe about 1 year ago

#27 - label leaks may happen?

Issue - State: open - Opened by LongLiveSocialism about 1 year ago - 4 comments

#26 - About the prompt for reflection

Issue - State: closed - Opened by Statisticss about 1 year ago - 4 comments

#25 - Content filtering using gpt3.5-turbo-16k

Issue - State: closed - Opened by ZhaoyangLi-1 about 1 year ago

#24 - About reflexion temperature(for HotpotQA)

Issue - State: closed - Opened by pengjiao123 about 1 year ago - 5 comments

#23 - Which commit matches your published work (for HumanEval-rs)?

Issue - State: open - Opened by geekoftheweek about 1 year ago - 5 comments

#22 - ModuleNotFoundError: No module named 'alfworld'

Issue - State: closed - Opened by uglyghost about 1 year ago - 1 comment

#21 - About the action limitation on Webshop

Issue - State: closed - Opened by zzh068 about 1 year ago

#20 - Implement AnyOpenAILLM for use across completion and chat endpoints

Pull Request - State: closed - Opened by becklabs over 1 year ago

#19 - [Bug] The success condition for alfworld might be incorrect

Issue - State: closed - Opened by stevenyangyj over 1 year ago - 8 comments

#18 - Update prompts.py

Pull Request - State: closed - Opened by rxlqn over 1 year ago - 2 comments
Labels: enhancement, help wanted

#17 - [Feature Request]: Gymnasium compatibility

Issue - State: open - Opened by elliottower over 1 year ago

#16 - Combine with Parsel for improving the state of the art?

Issue - State: closed - Opened by LifeIsStrange over 1 year ago - 1 comment

#15 - Merge Starchat into main

Pull Request - State: closed - Opened by cassanof over 1 year ago

#14 - Please integrate Reflexion into GPT-Engineer

Issue - State: closed - Opened by Emasoft over 1 year ago

#12 - What's the difference between these strategies

Issue - State: closed - Opened by gjm-anban over 1 year ago - 1 comment

#11 - HotpotQA oracle evaluator

Issue - State: closed - Opened by linyongnan over 1 year ago - 5 comments

#10 - commit for local llm runs

Pull Request - State: open - Opened by epinnock over 1 year ago

#9 - Hotpot notebooks

Pull Request - State: closed - Opened by becklabs over 1 year ago

#8 - merge in private

Pull Request - State: closed - Opened by cassanof over 1 year ago

#7 - HotPotQA runs

Pull Request - State: closed - Opened by becklabs over 1 year ago

#5 - How to run the code

Issue - State: closed - Opened by Mohitraj87 over 1 year ago - 1 comment

#4 - Add support for MultiPL-E

Issue - State: closed - Opened by Randl over 1 year ago - 1 comment

#3 - Interpreting results files

Issue - State: closed - Opened by sachit-menon over 1 year ago - 6 comments

#2 - "is_solved": false on all results

Issue - State: closed - Opened by drammen94 over 1 year ago - 2 comments

#1 - Add simple summary of the paper in README

Pull Request - State: closed - Opened by tornikeo over 1 year ago - 2 comments

GitHub / noahshinn/reflexion issues and pull requests