IBM Research

company

https://research.ibm.com/

AI & ML interests

Enterprise AI and ML, Foundation Models, Responsible AI

Recent Activity

Vatche published an article 2 days ago

Thinking of ACE? We Can Do It with Fewer Tokens

arielgera authored a paper about 2 months ago

Task-Adaptive Embedding Refinement via Test-time LLM Guidance

arielgera authored a paper about 2 months ago

Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering

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

View all Papers

Articles

Thinking of ACE? We Can Do It with Fewer Tokens

Model Routing Is Simple. Until It Isn’t.

ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration

Build real agentic apps using CUGA: two dozen working examples on a lightweight harness

Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic

ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM

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

published an article 2 days ago

Article

Thinking of ACE? We Can Do It with Fewer Tokens

ibm-research

•

2 days ago

• 27

authored 3 papers about 2 months ago

Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows

Paper • 2605.24219 • Published May 26 • 9

Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents

Paper • 2606.12674 • Published Jun 10 • 5

Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents

Paper • 2606.19704 • Published Jun 18 • 41

submitted a paper to Daily Papers about 2 months ago

Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents

Paper • 2606.19704 • Published Jun 18 • 41

authored 2 papers about 2 months ago

Task-Adaptive Embedding Refinement via Test-time LLM Guidance

Paper • 2605.12487 • Published May 12 • 1

Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering

Paper • 2606.10896 • Published Jun 9 • 6

authored 2 papers 3 months ago

GneissWeb: Preparing High Quality Data for LLMs at Scale

Paper • 2502.14907 • Published Feb 19, 2025 • 1

Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows

Paper • 2605.24219 • Published May 26 • 9

submitted a paper to Daily Papers 3 months ago

Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows

Paper • 2605.24219 • Published May 26 • 9

authored 3 papers 3 months ago

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

Paper • 2605.08614 • Published May 9 • 7

Code-Guided Reasoning for Small Language Models: Evaluating Executable MCQA Scaffolds

Paper • 2605.18827 • Published May 12 • 7

Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines

Paper • 2605.20630 • Published May 20 • 12

submitted 2 papers to Daily Papers 3 months ago

Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines

Paper • 2605.20630 • Published May 20 • 12

Code-Guided Reasoning for Small Language Models: Evaluating Executable MCQA Scaffolds

Paper • 2605.18827 • Published May 12 • 7

authored 5 papers 3 months 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 Apr 25 • 4

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

Paper • 2605.09131 • Published May 9 • 60

Results and Retrospective Analysis of the CODS 2025 AssetOpsBench Challenge

Paper • 2605.08518 • Published May 8 • 11

SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks

Paper • 2605.14051 • Published May 13 • 1