Tag Archive

benchmark 第9页

Explore tools, prompts, skills, news and resources related to benchmark 第9页.

On this page: 20 Prompts: 0 News: 20 Directory: 0

News & Insights

Latest articles, prompts, use cases and editorial content about benchmark 第9页

Top AI News Today 2026-11-10 13:00:00

CARE-PO: Controllable Tool-Call Efficiency for LLM Agents

The paper diagnoses Qwen3.5 agent trajectories on GAIA and reports that most contain removable tool calls at both model sizes studied. It argues that existing efficiency rewards use policy-dependent anchors, can drift to...

AI News 2026-11-09 13:00:00

On Agentic Manipulation Policies

A new arXiv paper analyzes agentic manipulation policies (AMPs), where a generalist AI model directly commands a robot manipulator and adapts actions as tasks unfold. The authors present AMP1, a reference harness that ru...