IBM Research

company

https://research.ibm.com/

AI & ML interests

Enterprise AI and ML, Foundation Models, Responsible AI

Recent Activity

rkrsn updated a dataset about 4 hours ago

ibm-research/ScarfBench

brmcg updated a dataset about 4 hours ago

ibm-research/ScarfBench

basels updated a dataset about 9 hours ago

ibm-research/WikiVQABench

View all activity

Papers

MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments

Results and Retrospective Analysis of the CODS 2025 AssetOpsBench Challenge

View all Papers

Articles

The Open Agent Leaderboard

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

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

IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST

AssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial Reality

CUGA on Hugging Face: Democratizing Configurable AI Agents

View all articles

ibm-research 's Papers 12

Submitted by

Dhaval Patel

MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments

ibm-research

2

Submitted by

Dhaval Patel

Results and Retrospective Analysis of the CODS 2025 AssetOpsBench Challenge

ibm-research

1

Submitted by

Dhaval Patel

IndustryAssetEQA: A Neurosymbolic Operational Intelligence System for Embodied Question Answering in Industrial Asset Maintenance

ibm-research

2

Submitted by

itay nakash

Efficient Agent Evaluation via Diversity-Guided User Simulation

ibm-research

Submitted by

Barzelay

VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents

ibm-research

Submitted by

Nimrod Shabtay

Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs

ibm-research

Submitted by

Leshem Choshen

General Agent Evaluation

ibm-research

Submitted by

HangHua

SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs

ibm-research

2

Submitted by

roi pony

Col-Bandit: Zero-Shot Query-Time Pruning for Late-Interaction Retrieval

ibm-research

2

CARES: Context-Aware Resolution Selector for VLMs

ibm-research

BMFM-DNA: A SNP-aware DNA foundation model to capture variant effects

ibm-research

BMFM-RNA: An Open Framework for Building and Evaluating Transcriptomic Foundation Models

ibm-research