IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST
•
15
AI & ML interests
Enterprise AI and ML, Foundation Models, Responsible AI
Recent Activity
Papers
SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs
Col-Bandit: Zero-Shot Query-Time Pruning for Late-Interaction Retrieval
Articles
ibm-research/AssetOpsBench
Viewer
• Updated
• 152 • 837 • 10
ibm-research/FailureSensorIQ
Viewer
• Updated
• 8.3k • 122 • 5
ibm-research/AITQARetrieval
Viewer
• Updated
• 3.99k • 13
ibm-research/WatsonxDocsQARetrieval
Viewer
• Updated
• 1.2k • 11
ibm-research/StatCanDialogueRetrieval
Viewer
• Updated
• 7.65k • 14
ibm-research/MultiHierttRetrieval
Viewer
• Updated
• 11.9k • 12
ibm-research/OTTQASmallRetrieval
Viewer
• Updated
• 31.1k • 20
ibm-research/NQTablesRetrieval
Viewer
• Updated
• 533k • 18
ibm-research/OpenWikiTablesRetrieval
Viewer
• Updated
• 178k • 25
ibm-research/FeTaQARetrieval
Viewer
• Updated
• 24.7k • 14
ibm-research/rag-hpo-bench
Preview
• Updated
• 53 • 2
ibm-research/acp_bench
Viewer
• Updated
• 3.72k • 1.78k • 13
ibm-research/data-product-benchmark
Viewer
• Updated
• 20.8k • 846 • 3
ibm-research/dp-bench
Updated
• 79 • 1
ibm-research/ITBench-Lite
Updated
• 9.19k • 5
ibm-research/ITBench-Trajectories
Updated
• 864 • 3
ibm-research/nc-bench
Viewer
• Updated
• 720 • 46 • 1
ibm-research/ReasonLab
Viewer
• Updated
• 4.35k • 151
ibm-research/Auto-BenchmarkCard
Viewer
• Updated
• 105 • 60 • 3
ibm-research/MermaidSeqBench
Viewer
• Updated
• 132 • 64 • 5
ibm-research/knowledge_consistency_of_LLMs
Preview
• Updated
• 57 • 3
ibm-research/ToolRM-train-data
Viewer
• Updated
• 459k • 130 • 7
ibm-research/BFCL-FC-robustness
Updated
• 9
ibm-research/SQL-API-Bench
Viewer
• Updated
• 3.41k • 290 • 4
ibm-research/fc-reward-bench
Viewer
• Updated
• 1.5k • 168 • 5
ibm-research/REAL-MM-RAG_TechReport_BEIR
Viewer
• Updated
• 5.57k • 28
ibm-research/REAL-MM-RAG_TechSlides_BEIR
Viewer
• Updated
• 6.09k • 41
ibm-research/REAL-MM-RAG_FinSlides_BEIR
Viewer
• Updated
• 5.5k • 71
ibm-research/REAL-MM-RAG_FinReport_BEIR
Viewer
• Updated
• 5.27k • 52 • 1
ibm-research/Split-IFEval
Viewer
• Updated
• 541 • 981 • 1