SkillsBench: A Benchmark for Evaluating AI Agent Skills Across Diverse Tasks
Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We…
Read the full articleYou might also wanna read
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
arXiv:2607.08768v1 Announce Type: new Abstract: The rapid development of large language models and multimodal large language models has acce
EdgeBench: A Benchmark for Measuring AI Environment Learning Through Extended Real-World Tasks
EdgeBench studies how agents learn from real-world environments across 134 day-long executable tasks.
edge-bench.org·14d ago
VideoWeaver: A Benchmark for Evaluating AI Agent Skills in Long Video Generation
Recent agent frameworks such as Claude Code, Codex, and OpenClaw are strong at tool use and orchestration, but whether they can handle long
arxiv.org·1mo ago
New Alibaba AI framework skips loading every tool, cutting agent token use 99%
As enterprise AI systems scale to handle complex workflows, practitioners face the challenge of routing subtasks to the right tools and skil
MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers
arXiv:2607.14642v1 Announce Type: new Abstract: As Model Context Protocol (MCP) servers emerge as the core infrastructure for connecting LLM
Skill-MAS: A Meta-Skill Approach to Improving Multi-Agent Systems Without Retraining
Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. Ho
arxiv.org·26d agoSkill-MAS: A Meta-Skill Approach to Improving Multi-Agent Systems Without Retraining
Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. Ho
arxiv.org·26d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.