[KongchangAI]
Unverified50% confidenceFactExact time

AgentBench was proposed in 2023 by a research team from Tsinghua University and other institutions, with the paper published at ICLR 2024; it is the first multi-dimensional benchmark to systematically evaluate LLMs' capabilities as agents.

1
Sources
50%
Confidence
Long-term
Relevance
9/10/2026
First Seen

Sources

Why Do LLM Agents Go Off the Rails After Three Steps? Causes and Solutions

Related Entities

AgentBenchproductTsinghua UniversitycompanyICLR 2024concept

Related Claims

UnverifiedAgent评估领域在2023-2024年经历了从人工评审到LLM-as-Judge再到结构化Rubric的演化77% similarUnverifiedThe Agent Skills architecture was further released as an open standard in December 2025, aimed at guiding a new AI development ecosystem.71% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/890352
API
curl https://kongchang.com/api/v1/knowledge/claims/890352
MCP
get_claim(id=890352)