Agent-Eval-Refine/Agent-Trajectories

Dataset

5

stars

16

commits

1

linked in READMEs

Apr 12, 2024

updated

README

  • trajectories.zip contains all trajectories evaluated in our paper, including

    • WebArena
      • GPT-4 CoT baseline agent extracted from WebArena official release
    • Android
      • Auto-UI base/large
      • CogAgent
      • Human demonstrations from Android-in-the-Wild
    • iOS
      • CogAgent basline
      • CogAgent + Self-training
      • CogAgent + Filtered BC
  • ios-offline-trajectories.zip contains CogAgent's trajectories on iOS emulator, which is then used to refine the CogAgent model through Filtered BC

  • webarena-reflexion-<evaluator-type).zip contains webarena trajectories on refining the GPT-4 CoT baseline with a model-based evaluator (Figure 3 of our paper)

    • GPT-4V
    • Captioner + GPT-4
    • Captioner + Mixtral
    • Oracle Evaluator

Contributors

594zyc

8 commits

Jiayi-Pan

8 commits

Agent-Eval-Refine/Agent-Trajectories

Dataset

5

stars

16

commits

1

linked in READMEs

Apr 12, 2024

updated

README

  • trajectories.zip contains all trajectories evaluated in our paper, including

    • WebArena
      • GPT-4 CoT baseline agent extracted from WebArena official release
    • Android
      • Auto-UI base/large
      • CogAgent
      • Human demonstrations from Android-in-the-Wild
    • iOS
      • CogAgent basline
      • CogAgent + Self-training
      • CogAgent + Filtered BC
  • ios-offline-trajectories.zip contains CogAgent's trajectories on iOS emulator, which is then used to refine the CogAgent model through Filtered BC

  • webarena-reflexion-<evaluator-type).zip contains webarena trajectories on refining the GPT-4 CoT baseline with a model-based evaluator (Figure 3 of our paper)

    • GPT-4V
    • Captioner + GPT-4
    • Captioner + Mixtral
    • Oracle Evaluator

Contributors

594zyc

8 commits

Jiayi-Pan

8 commits