#LLM Benchmarking

3 articles with this tag

Kimi Verifier Rebuilds Trust in Open Source AI
AI

Kimi Verifier Rebuilds Trust in Open Source AI

Moonshot AI launches Kimi Vendor Verifier to ensure open-source AI models run accurately across all implementations, rebuilding trust in the ecosystem.

about 1 month ago
Automating Visual Workflows with LLMs
AI Research

Automating Visual Workflows with LLMs

A new benchmark, Chat2Workflow, reveals LLMs struggle with generating executable visual workflows, despite progress in capturing intent. A significant gap remains for industrial automation.

4 months ago
AI Agents Tackle AI R&D Automation
AI Research

AI Agents Tackle AI R&D Automation

AI agents are being tested for autonomous post-training optimization, showing promise but also significant risks like reward hacking.

5 months ago