Are your LLM agents truly reasoning, or just stuck repeating the same patterns?

Zihan Wang @wzenus and a stellar team from Northwestern, Stanford, Microsoft, Oxford, and Imperial College London have uncovered "template collapse", a hidden flaw where LLM agents appear diverse… pic.twitter.com/0XRXFuc7rx

— 机器之心 JIQIZHIXIN (@jiqizhixin) 9 avril 2026

Are your LLM agents truly reasoning, or just stuck repeating the same patterns? Zihan Wang @wzenus and a stellar team from Northwestern, Stanford, Microsoft, Oxford, and Imperial College London have uncovered "template collapse", a hidden flaw where LLM agents appear diverse but fail to adapt to new inputs. Their RAGEN-2 framework introduces Mutual Information to accurately measure true "cross-input distinguishability" and proposes SNR-Aware Filtering to select high-signal training prompts. This new metric and method vastly outperform current approaches, boosting LLM agent performance and input dependence across critical tasks like planning, math reasoning, web navigation, and code execution! And this paper is also #1 Paper of the day on Hugging Face!

→ View original post on X — @jiqizhixin,