noahshinn/reflexion

Issues

• How to run a specific alfworld environment?

  #34 opened 10 months ago by ai-nikolai
  2

• HotpotQA oracle evaluator

  #11 opened a year ago by linyongnan
  5

• Using Ground Truth in Evaluator for HotpotQA

  #45 opened 3 months ago by Skevinci
  1

• actor in webshop does not intake the memory and relfexion

  #36 opened 10 months ago by yananchen1989
  7

• Why i receive this warning

  #44 opened 3 months ago by beishangeyu
  0

• Using CodeLLAMA cause the program crash

  #39 opened 8 months ago by allanj
  4

• Can use local LLM？not openai api

  #38 opened 8 months ago by liucheny
  5

• Inconsistencies with the humaneval dataset

  #42 opened 3 months ago by HamedTaherkhani
  3

• Reproducing HotpotQA Results

  #43 opened 3 months ago by haoyb22
  0

• Always fails to execute the action, and it responds with 'nothing happens'.

  #41 opened 7 months ago by prettystar0203
  1

• Reproducing Alfworld Results

  #35 opened 10 months ago by ai-nikolai
  9

• Script for leetcode results

  #29 opened a year ago by shenao-zhang
  1

• About reflexion temperature(for HotpotQA)

  #24 opened 7 months ago by pengjiao123
  5

• Can't reproduce HumanEval score

  #30 opened 10 months ago by geekan
  5

• Potential unexpected behavior in executor (that uses the`global`)

  #40 opened 8 months ago by allanj
  5

• Prompt for Llama-2-7b-chat-hf model

  #37 opened 8 months ago by oximi123
  0

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

  #23 opened a year ago by geekoftheweek
  5

• ValueError: AlfWorld Environment [expert_plan, expert_type]

  #31 opened 10 months ago by ai-nikolai
  1

• Clarification on ReflexionStrategy Implementation

  #28 opened 10 months ago by zapqqqwe
  0

• label leaks may happen?

  #27 opened a year ago by LongLiveSocialism
  4

• About the action limitation on Webshop

  #21 opened 10 months ago by zzh068
  0

• ModuleNotFoundError: No module named 'alfworld'

  #22 opened 10 months ago by uglyghost
  1

• what's the difference between COT_INSTRUCTION & COT_AGENT_REFLECT_INSTRUCTION in prompts.py

  #32 opened 10 months ago 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 10 months ago by huayicong23
  0

• About the prompt for reflection

  #26 opened a year ago by Statisticss
  4

• Content filtering using gpt3.5-turbo-16k

  #25 opened a year ago by ZhaoyangLi-1
  0

• [Bug] The success condition for alfworld might be incorrect

  #19 opened a year ago by stevenyangyj
  8

• [Feature Request]: Gymnasium compatibility

  #17 opened a year ago by elliottower
  0

• Combine with Parsel for improving the state of the art?

  #16 opened a year ago by LifeIsStrange
  1

• How to run the code

  #5 opened a year ago by Mohitraj87
  1

• Please integrate Reflexion into GPT-Engineer

  #14 opened a year ago by Emasoft
  0

• Add support for MultiPL-E

  #4 opened a year ago by Randl
  1

• "is_solved": false on all results

  #2 opened a year ago by drammen94
  2

• What's the difference between these strategies

  #12 opened a year ago by gjm-anban
  1

• Interpreting results files

  #3 opened 2 years ago by sachit-menon
  6