AI Agents

Autonomous agents, multi-agent workflows and orchestration.

1 published article

AI Agents

AI agents can't finish a Java migration without the build server telling them to stop

IBM Research introduces ScarfBench, an open benchmark for evaluating AI agents on enterprise Java framework migration. Early tests reveal that frontier agents are systematically overconfident about their own results, that configuration layers dominate effort, and that environment issues like Docker caches regularly derail migrations even when code transformations succeed.

2026-07-06

Discover other categories

IBM's open-source CUGA agent harness skips the plumbing, goes straight to the prompt

2026-07-07

TCS and Anthropic Partner to Bring Claude to Regulated Industries

2026-07-07

LLMs & Models

Your AI agent passed the test by accident. Now there's a rubric for that.

2026-07-06

Ai2's olmo-eval gives LLM developers a microscope for every checkpoint

2026-07-06

Phi-4

Microsoft's Phi-4 Model Redefines Efficiency in Breakthrough Research

2026-07-03