AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Paper • 2609.38288 • Published • 65
JUNJIE ZHOU
JUNJIE99
AI & ML interests
None yet
Recent Activity
upvoted a paper about 3 hours ago
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks liked a model 1 day ago
BAAI/AREX-2 new activity 15 days ago
TIGER-Lab/MMEB-Leaderboard:Corrections to the PeerQA and DeepPlanning scores of WeMM modelsOrganizations
upvoted a paper about 3 hours ago
liked a
model 1 day ago
Corrections to the PeerQA and DeepPlanning scores of WeMM models
1
#188 opened 15 days ago
by JUNJIE99
updated 3
models 28 days ago
upvoted a paper 28 days ago
update meta info for wemm-embedding
1
#182 opened about 1 month ago
by JUNJIE99
authored a
paper about 1 month ago
Fix score aggregation: exclude MCMR from Overall-V2, use nDCG@5 for text
1
#180 opened about 1 month ago
by JUNJIE99
updated a
collection about 1 month ago
upvoted a paper about 1 month ago
submitted a
paper to Daily Papers about 1 month ago
Integrate with Sentence Transformers, restore training-time tokenization on newer transformers
1
#1 opened about 1 month ago
by 
tomaarsen
Integrate with Sentence Transformers, restore training-time tokenization on newer transformers
1
#1 opened about 1 month ago
by tomaarsen
Integrate with Sentence Transformers, restore training-time tokenization on newer transformers
👍 1
4
#1 opened about 1 month ago
by tomaarsen
MMEB-WeMM-submission
2
#179 opened about 1 month ago
by JUNJIE99
liked 3
models about 1 month ago