EvoAgentBench

What is EvoAgentBench?

EvoAgentBench evaluates agent self-evolution via ability transfer across web research, algorithmic reasoning, software engineering, and knowledge work, using…

Released

2026-07-06

Evaluates

Agents, Code, Code & Software, Factuality, General AI, Reasoning, Self-Evolution, Software & AI Compute

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.05202

EvoAgentBench paper and dataset

• Paper https://arxiv.org/abs/2607.05202
• Dataset https://huggingface.co/datasets/EverMind-AI/EvoAgentBench

Which sources cite EvoAgentBench?

• EvoAgentBench

Related Agents, Code, Code & Software, Factuality, General AI, Reasoning, Self-Evolution, Software & AI Compute benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A-OKVQA
• A3S-Bench
• AARRI-Bench
• ActBench
• Active-SWE