KnowledgeXLab/MemHarness
Viewer • Updated • 880 • 44
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
MemHarness: Memory Is Reconstructed, Not Replayed
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals
EdaiziÂ
updated a
dataset 8 days ago
EdaiziÂ
published a
dataset 8 days ago
Add model card
#1 opened 15 days ago
by 
nielsr
EdaiziÂ
updated a
model 15 days ago
EdaiziÂ
published a
model 16 days ago
EdaiziÂ
submitted a
paper to Daily Papers 16 days ago
EdaiziÂ
authored 2
papers 26 days ago
fudaochengÂ
updated a
model about 1 month ago
fudaochengÂ
submitted a
paper to Daily Papers about 1 month ago
fudaochengÂ
published a
model about 1 month ago
julyaiÂ
updated a
model about 2 months ago
Wayne-lcÂ
published a
model about 2 months ago
EdaiziÂ
authored 6
papers 7 months ago
O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering
Paper • 2505.16582 • Published
IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?
Paper • 2509.24709 • Published • 7
LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval
Paper • 2508.10391 • Published
RE-Searcher: Robust Agentic Search with Goal-oriented Planning and Self-reflection
Paper • 2509.26048 • Published • 7
Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
Paper • 2510.08002 • Published • 24
The Agent's First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios
Paper • 2601.08173 • Published • 9
JianbiaoÂ
authored a
paper 7 months ago