The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2606. 06635v1 Announce Type: cross Abstract: Failures in language model reasoning emerge through distinct processes that leave identifiable signatures in the reasoning trace.
The paper presents a mechanistic analysis of how large language models solve grade‑school math word problems. It identifies a four‑stage sequential pipeline—Schema Abstraction, Operation Planning, Operand Binding, and Computation—each represented in distinct layer bands. The study shows that inserting an irrelevant clause disrupts the Operation Planning stage, pinpointing the cause of failure to specific attention heads.
arXiv:2602.02427v3 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved significant breakthroughs across various domains, but they can still produce unreliable or misleading ou...
arXiv:2610.18127v1 Announce Type: new Abstract: Looped language models (LMs) reuse one block of layers several times per token generation, promising more latent computation at no additional storage c...
arXiv:2608. 03291v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning improves large language model (LLM) performance while also providing an observable interface to the model's reasoning process.
CritICL is an inference-time framework that enhances reasoning in large language models by using failure patterns from weaker models as critique-based in-context examples. It offers two variants: CritICL-dynamic, which predicts input-specific failure modes, and CritICL-static, which applies a global failure mode profile. Experiments show that CritICL outperforms standard in-context learning and rivals test-time scaling methods while using fewer generations and lower token costs.