IBM Research

company

https://research.ibm.com/

AI & ML interests

Enterprise AI and ML, Foundation Models, Responsible AI

Recent Activity

ChathurangiShyalika authored a paper about 5 hours ago

SmartPilot: A Multiagent CoPilot for Adaptive and Intelligent Manufacturing

ChathurangiShyalika authored a paper about 5 hours ago

Results and Retrospective Analysis of the CODS 2025 AssetOpsBench Challenge

Elron published an article about 24 hours ago

The Open Agent Leaderboard

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

about 24 hours ago

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

published an article about 24 hours ago

Article

The Open Agent Leaderboard

ibm-research

•

about 24 hours ago

• 5

authored 5 papers 1 day ago

SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search

Paper • 2512.23167 • Published Dec 29, 2025 • 1

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

Paper • 2604.23446 • Published 25 days ago • 4

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

Paper • 2605.09131 • Published 11 days ago • 49

Results and Retrospective Analysis of the CODS 2025 AssetOpsBench Challenge

Paper • 2605.08518 • Published 12 days ago • 10

SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks

Paper • 2605.14051 • Published 7 days ago • 1

submitted a paper to Daily Papers 1 day ago

DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules

Paper • 2605.08614 • Published 11 days ago • 6

submitted a paper to Daily Papers 5 days ago

SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks

Paper • 2605.14051 • Published 7 days ago • 1

submitted 2 papers to Daily Papers 6 days ago

Results and Retrospective Analysis of the CODS 2025 AssetOpsBench Challenge

Paper • 2605.08518 • Published 12 days ago • 10

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

Paper • 2605.09131 • Published 11 days ago • 49

submitted a paper to Daily Papers 21 days ago

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

Paper • 2604.23446 • Published 25 days ago • 4

submitted a paper to Daily Papers 22 days ago

Video Analysis and Generation via a Semantic Progress Function

Paper • 2604.22554 • Published 26 days ago • 63

authored 3 papers 22 days ago

ChartGen: Scaling Chart Understanding Via Code-Guided Synthetic Chart Generation

Paper • 2507.19492 • Published May 31, 2025 • 1

Composition-Grounded Instruction Synthesis for Visual Reasoning

Paper • 2510.15040 • Published Oct 16, 2025

ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding

Paper • 2603.27064 • Published Mar 28 • 28

authored a paper about 2 months ago

From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

Paper • 2603.22386 • Published Mar 23 • 57

authored 4 papers 2 months ago

KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents

Paper • 2405.00505 • Published May 1, 2024

Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence

Paper • 2502.09927 • Published Feb 14, 2025

REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark

Paper • 2502.12342 • Published Feb 17, 2025 • 7

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

Paper • 2602.02827 • Published Feb 2 • 3