Code

Significant updates to agbench.#5313

Code

Merged

afourney merged 34 commits intomainmicrosoft/autogen:mainfrom update_agbenchmicrosoft/autogen:update_agbenchCopy head branch name to clipboardFeb 7, 2025

+793-2,687

Commits

Commits on Feb 1, 2025

• Significant updates to agbench.

  afourney

  committed
  6b7cc8e

  Copy full SHA for 6b7cc8e

• Fixed some plubming issues.

  afourney

  committed
  cd065f6

  Copy full SHA for cd065f6

• Fixed GAIA support.

  afourney

  committed
  d15af5b

  Copy full SHA for d15af5b

Commits on Feb 3, 2025

• Updated config to allow different models to be used with M1

  afourney

  committed
  db6964b

  Copy full SHA for db6964b

• Use javascript to determine what text is visible in WebSurfer's viewport.

  afourney

  committed
  3dd0f5f

  Copy full SHA for 3dd0f5f

• Merge remote-tracking branch 'origin/viewport_text' into update_agbench

  afourney

  committed
  f11c4ed

  Copy full SHA for f11c4ed

Commits on Feb 4, 2025

• Merge remote-tracking branch 'origin/main' into update_agbench

  afourney

  committed
  13c5445

  Copy full SHA for 13c5445

Commits on Feb 5, 2025

• Added official GAIA scorer.

  afourney

  committed
  bfede70

  Copy full SHA for bfede70

• Prompting changes to better support smaller models.

  afourney

  committed
  3d73b0d

  Copy full SHA for 3d73b0d

Commits on Feb 6, 2025

• Merge branch 'main' into llama_surfer

  afourney

  authored
  ae2c4b3

  Copy full SHA for ae2c4b3

• Fixed summarization.

  afourney

  committed
  4fd3b17

  Copy full SHA for 4fd3b17

• Merge main.

  afourney

  committed
  b208068

  Copy full SHA for b208068

• Merge remote-tracking branch 'origin/llama_surfer' into update_agbench

  afourney

  committed
  da3dcff

  Copy full SHA for da3dcff

• Ensure decriptions appear each on one line. Fix web_surfer's description.

  afourney

  committed
  f55c66b

  Copy full SHA for f55c66b

• Merge remote-tracking branch 'origin/fix_m1_descriptions' into llama_surfer

  afourney

  committed
  de13d57

  Copy full SHA for de13d57

• Remove erroneous print

  afourney

  committed
  946d845

  Copy full SHA for 946d845

• Various web surfer fixes.

  afourney

  committed
  6dd88ac

  Copy full SHA for 6dd88ac

• Merge fixes.

  afourney

  committed
  63ef5b3

  Copy full SHA for 63ef5b3

• Merge remote-tracking branch 'origin/llama_surfer' into update_agbench

  afourney

  committed
  e32e6f7

  Copy full SHA for e32e6f7

• applied more patches

  afourney

  committed
  aa8f820

  Copy full SHA for aa8f820

• Merged main.

  afourney

  committed
  3bf9c6f

  Copy full SHA for 3bf9c6f

• Merge remote-tracking branch 'origin/llama_surfer' into update_agbench

  afourney

  committed
  c3c4092

  Copy full SHA for c3c4092

• Merge fixes.

  afourney

  committed
  5a09868

  Copy full SHA for 5a09868

Commits on Feb 7, 2025

• Merge main.

  afourney

  committed
  6613b12

  Copy full SHA for 6613b12

• Added GroupChatSelector template.

  afourney

  committed
  fcd57c0

  Copy full SHA for fcd57c0

• Removed older benchmarks that were missing Templates. These will return in a later PR.

  afourney

  committed
  0caf62f

  Copy full SHA for 0caf62f

• Missed a file.

  afourney

  committed
  a710b7a

  Copy full SHA for a710b7a

• Merge branch 'main' into update_agbench

  afourney

  authored
  f022d7f

  Copy full SHA for f022d7f

• Fixed mypy.

  afourney

  committed
  c45d701

  Copy full SHA for c45d701

• Updated READMEs.

  afourney

  committed
  289b166

  Copy full SHA for 289b166

• Fixed pyright.

  afourney

  committed
  cc64309

  Copy full SHA for cc64309

• Trying to fix types again.

  afourney

  committed
  83ac692

  Copy full SHA for 83ac692

• Fixed formatting.

  afourney

  committed
  462a975

  Copy full SHA for 462a975

• Merge branch 'main' into update_agbench

  afourney

  authored
  7125e29

  Copy full SHA for 7125e29