agential icon indicating copy to clipboard operation
agential copied to clipboard

Published 20 hours ago • verified publisher icon agential-ai

[Feature Request]: Reflexion

Open alckasoc opened this issue 9 months ago • 0 comments

Feature Description

Implement:

  • [x] HotpotQA
  • [x] #123
  • [x] #122
  • [x] #124
  • [x] #125
  • [x] #126
  • [x] #127
  • [x] #128
  • [x] #129
  • [ ] #131
  • [ ] #132
  • [ ] #133 (includes ALFWorld & WebShop)

The decision-making benchmarks (ALFWorld, WebShop, and AgentBench) will require more design work. Swapping out the prompts won't suffice.

Run:

  • [ ] HotpotQA
  • [ ] TriviaQA
  • [ ] AmbigNQ
  • [ ] GSM8k
  • [ ] SVAMP
  • [ ] TabMWP
  • [ ] MBPP
  • [ ] HumanEval
  • [ ] ALFWorld
  • [ ] WebShop
  • [ ] AgentBench (includes ALFWorld & WebShop)

alckasoc avatar Apr 30 '24 10:04 alckasoc