Your Agent Aced the Task. Will It Do It Again?
• 105
AI & ML interests
Enterprise AI and ML, Foundation Models, Responsible AI
Papers
DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
Articles
A collection of time series models trained by IBM
-
ibm-research/ttm-research-r2
Time Series Forecasting • 855k • Updated • 3.89k • 8 -
ibm-research/ttm-r3
Time Series Forecasting • 1.41M • Updated • 6.08k • 8 -
ibm-research/flowstate
Time Series Forecasting • 9.07M • Updated • 71.2k • 13 -
ibm-research/patchtst-fm-r1
Time Series Forecasting • 0.3B • Updated • 38.8k • 9
An evaluation suite created for benchmarking of retrieval models on Table+Text retrieval datasets.
This category highlights the collective efforts of the AI Automation team in advancing Industry 4.0 applications and exploring innovations beyond it.
-
AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance
Paper • 2506.03828 • Published • 20 -
FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes
Paper • 2506.03278 • Published • 7 -
ibm-research/AssetOpsBench
Viewer • Updated • 467 • 838 • 46 -
AssetOpsBench
📉4Evaluating Autonomous AI Agents for Industry 4.0 Tasks
REAL-MM-RAG-Bench is a benchmark designed to evaluate multi-modal retrieval models under realistic and challenging conditions.
Welcome to IBM’s multi-modal foundation model for materials, FM4M, designed to support and advance research in materials science and chemistry.
Enterprise agent ecosystem featuring AssetOpsBench (industrial) and ITBench (SRE, FinOps, CISO), CUGA to accelerate AI Automation
-
CUGA Apps
🚀592 dozen real-life agents optimized for open models & stack
-
AssetOpsBench
🚀24Benchmark asset operation performance in the browser
-
CUGA Agent
🤖105Configurable Generalist Agent, leader in AppWorld Benchmark
-
MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
Paper • 2605.09131 • Published • 61
REAL-MM-RAG-Bench is a benchmark designed to evaluate multi-modal retrieval models under realistic and challenging conditions.
-
ibm-research/REAL-MM-RAG_FinReport_BEIR
Viewer • Updated • 5.27k • 200 • 2 -
ibm-research/REAL-MM-RAG_FinSlides_BEIR
Viewer • Updated • 5.5k • 199 • 1 -
ibm-research/REAL-MM-RAG_TechReport_BEIR
Viewer • Updated • 5.57k • 175 • 1 -
ibm-research/REAL-MM-RAG_TechSlides_BEIR
Viewer • Updated • 6.09k • 201 • 1
Datasets and models of the Otter-Knowledge project
GGUF-formatted versions of IBM Granite 3.2 models. Licensed under the Apache 2.0 license.
-
ibm-research/granite-3.2-2b-instruct-GGUF
Text Generation • 3B • Updated • 1.41k • 13 -
ibm-research/granite-3.2-8b-instruct-GGUF
Text Generation • 8B • Updated • 1.14k • 11 -
ibm-research/granite-vision-3.2-2b-GGUF
3B • Updated • 740 • 15 -
ibm-research/granite-guardian-3.2-3b-a800m-GGUF
Text Generation • 3B • Updated • 197 • 5
A collection of time series models trained by IBM
-
ibm-research/ttm-research-r2
Time Series Forecasting • 855k • Updated • 3.89k • 8 -
ibm-research/ttm-r3
Time Series Forecasting • 1.41M • Updated • 6.08k • 8 -
ibm-research/flowstate
Time Series Forecasting • 9.07M • Updated • 71.2k • 13 -
ibm-research/patchtst-fm-r1
Time Series Forecasting • 0.3B • Updated • 38.8k • 9
Enterprise agent ecosystem featuring AssetOpsBench (industrial) and ITBench (SRE, FinOps, CISO), CUGA to accelerate AI Automation
-
CUGA Apps
🚀592 dozen real-life agents optimized for open models & stack
-
AssetOpsBench
🚀24Benchmark asset operation performance in the browser
-
CUGA Agent
🤖105Configurable Generalist Agent, leader in AppWorld Benchmark
-
MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
Paper • 2605.09131 • Published • 61
An evaluation suite created for benchmarking of retrieval models on Table+Text retrieval datasets.
REAL-MM-RAG-Bench is a benchmark designed to evaluate multi-modal retrieval models under realistic and challenging conditions.
-
ibm-research/REAL-MM-RAG_FinReport_BEIR
Viewer • Updated • 5.27k • 200 • 2 -
ibm-research/REAL-MM-RAG_FinSlides_BEIR
Viewer • Updated • 5.5k • 199 • 1 -
ibm-research/REAL-MM-RAG_TechReport_BEIR
Viewer • Updated • 5.57k • 175 • 1 -
ibm-research/REAL-MM-RAG_TechSlides_BEIR
Viewer • Updated • 6.09k • 201 • 1
This category highlights the collective efforts of the AI Automation team in advancing Industry 4.0 applications and exploring innovations beyond it.
-
AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance
Paper • 2506.03828 • Published • 20 -
FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes
Paper • 2506.03278 • Published • 7 -
ibm-research/AssetOpsBench
Viewer • Updated • 467 • 838 • 46 -
AssetOpsBench
📉4Evaluating Autonomous AI Agents for Industry 4.0 Tasks
Datasets and models of the Otter-Knowledge project
REAL-MM-RAG-Bench is a benchmark designed to evaluate multi-modal retrieval models under realistic and challenging conditions.
GGUF-formatted versions of IBM Granite 3.2 models. Licensed under the Apache 2.0 license.
-
ibm-research/granite-3.2-2b-instruct-GGUF
Text Generation • 3B • Updated • 1.41k • 13 -
ibm-research/granite-3.2-8b-instruct-GGUF
Text Generation • 8B • Updated • 1.14k • 11 -
ibm-research/granite-vision-3.2-2b-GGUF
3B • Updated • 740 • 15 -
ibm-research/granite-guardian-3.2-3b-a800m-GGUF
Text Generation • 3B • Updated • 197 • 5
Welcome to IBM’s multi-modal foundation model for materials, FM4M, designed to support and advance research in materials science and chemistry.