Merve Unuvar

mrvnvr's activity

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

upvoted an article 6 days ago

view article

Article

ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model

• 

ibm-research

•

6 days ago

• 26

published an article 6 days ago

view article

Article

ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model

• 

ibm-research

•

6 days ago

• 26

upvoted an article about 1 month ago

view article

Article

Your Agent Aced the Task. Will It Do It Again?

• 

ibm-research

•

Sep 15

• 122

published an article about 1 month ago

view article

Article

Your Agent Aced the Task. Will It Do It Again?

• 

ibm-research

•

Sep 15

• 122

upvoted an article about 2 months ago

view article

Article

IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license

• 

ibm-research

•

Sep 9

• 60

liked a Space about 2 months ago

Running

24

AssetOpsBench

🚀

24

Run a quick benchmark of web asset performance

upvoted a collection about 2 months ago

Enterprise Agents and Benchmarks

Collection

Enterprise agent ecosystem featuring AssetOpsBench (industrial) and ITBench (SRE, FinOps, CISO), CUGA to accelerate AI Automation • 22 items • Updated Sep 4 • 21

upvoted a paper about 2 months ago

DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training

Paper • 2609.04094 • Published Sep 3 • 27

published an article 2 months ago

view article

Article

How Much Memory Does Your Agent Actually Need?

• 

ibm-research

•

Aug 18

• 83

upvoted an article 3 months ago

view article

Article

Thinking of ACE? We Can Do It with Fewer Tokens

• 

ibm-research

•

Aug 11

• 33

published an article 3 months ago

view article

Article

Thinking of ACE? We Can Do It with Fewer Tokens

• 

ibm-research

•

Aug 11

• 33

upvoted an article 3 months ago

view article

Article

Model Routing Is Simple. Until It Isn’t.

• 

ibm-research

•

Jul 15

• 95

published an article 3 months ago

view article

Article

Model Routing Is Simple. Until It Isn’t.

• 

ibm-research

•

Jul 15

• 95

liked a Space 4 months ago

Running

Featured

60

CUGA Apps

🚀

60

Explore and launch CUGA apps from a single dashboard

liked a dataset 4 months ago

ArtificialAnalysis/ITBench-AA

Viewer • Updated May 27 • 40 • 9.72k • 48

upvoted an article 4 months ago

view article

Article

Build real agentic apps using CUGA: two dozen working examples on a lightweight harness

• 

ibm-research

•

Jun 23

• 40

upvoted an article 5 months ago

view article

Article

Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic

• 

ibm-research

•

Jun 1

• 92

upvoted an article 6 months ago

view article

Article

Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents

• 

ibm-research

•

Apr 15

• 30

upvoted an article 7 months ago

view article

Article

ALTK‑Evolve: On‑the‑Job Learning for AI Agents

• 

ibm-research

•

Apr 8

• 32

liked a dataset 7 months ago

ibm-research/VAKRA

Viewer • Updated Sep 14 • 1.8k • 21.8k • 48