Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic
• 85
AI & ML interests
Enterprise AI and ML, Foundation Models, Responsible AI
Recent Activity
View all activity
Papers
Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering
Articles
ibm-research/AssetOpsBench
Viewer • Updated • 467 • 1.17k • 31
ibm-research/ScarfBench
Updated • 243 • 6
ibm-research/WikiVQABench
Viewer • Updated • 344 • 191 • 6
ibm-research/LLM_Fine-Tuning_Performance
Preview • Updated • 148 • 2
ibm-research/AITQARetrieval
Viewer • Updated • 3.99k • 104
ibm-research/cif-dataset
Viewer • Updated • 301k • 6.45k • 5
ibm-research/hemolab-bench
Viewer • Updated • 49.7k • 852 • 2
ibm-research/MermaidSeqBench
Viewer • Updated • 132 • 133 • 5
ibm-research/STaD
Preview • Updated • 47 • 1
ibm-research/ITBench-Lite
Updated • 5.51k • 5
ibm-research/VAKRA
Viewer • Updated • 1.33k • 1.91k • 44
ibm-research/data-product-benchmark
Viewer • Updated • 33.2k • 2.12k • 3
ibm-research/900K-Judgements
Viewer • Updated • 939k • 137 • 3
ibm-research/VAREX
Viewer • Updated • 1.78k • 2.48k • 4
ibm-research/BPO-Bench
Preview • Updated • 120 • 1
ibm-research/watsonxDocsQA
Viewer • Updated • 1.22k • 98 • 5
ibm-research/flow-bench
Viewer • Updated • 546 • 12 • 2
ibm-research/FailureSensorIQ
Viewer • Updated • 8.3k • 310 • 7
ibm-research/WatsonxDocsQARetrieval
Viewer • Updated • 1.2k • 120
ibm-research/StatCanDialogueRetrieval
Viewer • Updated • 7.65k • 81
ibm-research/MultiHierttRetrieval
Viewer • Updated • 11.9k • 50 • 1
ibm-research/OTTQASmallRetrieval
Viewer • Updated • 31.1k • 77 • 1
ibm-research/NQTablesRetrieval
Viewer • Updated • 533k • 129 • 2
ibm-research/OpenWikiTablesRetrieval
Viewer • Updated • 178k • 73 • 1
ibm-research/FeTaQARetrieval
Viewer • Updated • 24.7k • 53
ibm-research/rag-hpo-bench
Preview • Updated • 2.52k • 2
ibm-research/acp_bench
Viewer • Updated • 3.72k • 1.36k • 13
ibm-research/dp-bench
Updated • 50 • 1
ibm-research/ITBench-Trajectories
Updated • 442 • 3
ibm-research/nc-bench
Viewer • Updated • 720 • 99 • 1