i-DeepSearch

i-DeepSearch's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

IPF 

updated a dataset about 8 hours ago

i-DeepSearch/browsecomp-plus-traces

Viewer • Updated about 8 hours ago • 1 • 846

Racktic 

updated a dataset 1 day ago

i-DeepSearch/browsecomp-plus-traces

Viewer • Updated about 8 hours ago • 1 • 846

Racktic 

authored a paper 5 days ago

MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI

Paper • 2605.08678 • Published 9 days ago • 8

IPF 

authored a paper 7 days ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published 15 days ago • 107

IPF 

updated a dataset 10 days ago

i-DeepSearch/index-reason-moderncolbert-plaid-browsecomp-plus

Updated 10 days ago • 139

IPF 

published a dataset 10 days ago

i-DeepSearch/index-reason-moderncolbert-plaid-browsecomp-plus

Updated 10 days ago • 139

IPF 

updated a dataset 11 days ago

i-DeepSearch/index-reason-moderncolbert-browsecomp-plus

Updated 11 days ago • 41

IPF 

published a dataset 11 days ago

i-DeepSearch/index-reason-moderncolbert-browsecomp-plus

Updated 11 days ago • 41

IPF 

in i-DeepSearch/browsecomp-plus-traces 12 days ago

Add traces: qwen3.5-9b-agentir-parallel, qwen3.5-9b-agentir-parallel-auto-only, qwen3.5-9b-bm25-parallel

#2 opened 12 days ago by

IPF

Update README

#1 opened 12 days ago by

IPF

IPF 

published a dataset 12 days ago

i-DeepSearch/browsecomp-plus-traces

Viewer • Updated about 8 hours ago • 1 • 846

IPF 

authored a paper about 1 month ago

CocoaBench: Evaluating Unified Digital Agents in the Wild

Paper • 2604.11201 • Published Apr 13 • 36

IPF 

authored a paper about 2 months ago

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

Paper • 2603.20278 • Published Mar 17 • 98

Racktic 

authored 2 papers 8 months ago

Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning

Paper • 2509.03646 • Published Sep 3, 2025 • 33

Reverse-Engineered Reasoning for Open-Ended Generation

Paper • 2509.06160 • Published Sep 7, 2025 • 151

Racktic 

authored a paper over 1 year ago

Process Reinforcement through Implicit Rewards

Paper • 2502.01456 • Published Feb 3, 2025 • 62