The paper examines the compositionality gap in GPT‑2‑like transformers, where models can combine known facts in‑distribution but fail to generalize to out‑of‑distribution knowledge. By aligning the training distribution so that both ID and OOD atomic facts appear in the same positional format as the second‑hop retrieval step of a known compositional circuit, the authors show that the model can transfer its learned compositional behavior to unseen OOD facts. This demonstrates that the gap is not an inherent architectural limitation but can be addressed through targeted training distribution design.
By Davide Venuto, Leonardo Venuto
Large language models can solve complex multi‑hop tasks but often fail on simple two‑hop queries, even when each hop is individually correct. In a controlled symbolic setting, the authors find that models generalize reliably when the second hop follows the training distribution, but always fail when it deviates. Mechanistic analysis shows that successful generalization relies on consistent intermediate representations across contexts, whereas failures arise from a mismatch between lower‑layer representation construction and upper‑layer mapping to outputs. The study proposes a recurrent‑style training strategy that improves out‑of‑distribution two‑hop generalization.
By Zili Zhang, Yilin Wang, Heng Wang, Herun Wan, Minnan Luo
arXiv:2505.22635v2 Announce Type: replace-cross
Abstract: A common approach for teaching large language models (LLMs) to reason is to train on chain-of-thought (CoT) traces of in-distribution reasoni...
By Fangcong Yin, Zeyu Leo Liu, Liu Leqi, Xi Ye, Greg Durrett
arXiv:2509. 24653v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) excel at multi-hop reasoning in distribution, yet fail on unseen compositions, a phenomenon known as the curse of two-hop reasoning.
By Pengxiao Lin, Zheng-An Chen, Zhi-Qin John Xu
arXiv:2604. 07822v2 Announce Type: replace-cross Abstract: We study implicit reasoning, i.
By Harsh Kohli, Srinivasan Parthasarathy, Huan Sun, Yuekun Yao
arXiv:2607. 11875v1 Announce Type: cross Abstract: We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models.
By Tiberiu Musat, Tiago Pimentel, Nicholas Zucchet, Thomas Hofmann
We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models. While previous works on Transformer learning dynamics have so far been mostly tied to specific tasks, we study a generalized class of inductive tasks that unifies several synthetic tasks known in the literature, including in-context n-grams and multi-hop reasoning.
arXiv:2607. 00341v1 Announce Type: cross Abstract: Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT).
By Hengyu Fu, Tianyu Guo, Zixuan Wang, Hanlin Zhu, Jason D. Lee, Jiantao Jiao, Stuart Russell, Song Mei
arXiv:2607. 15178v1 Announce Type: cross Abstract: Transformer reasoning is limited by autoregressive decoding, which repeat edly compresses rich hidden computation through token space and makes it difficult for intermediate reasoning states to persist across time.
By Ziyang Cai, Xingyu Zhu, Yihe Dong, Yinghui He, Sanjeev Arora
The State Stream Transformer (SST) V2 introduces a parameter‑efficient, FFN‑driven nonlinear recurrence that streams latent states horizontally across a sequence, enabling continuous latent deliberation at inference time. A two‑pass parallel training procedure approximates this recurrence, making co‑training practical. Experiments on GSM8K and GPQA‑Diamond show that SST achieves a 61.11% architectural capacity bound and a 15.15‑point improvement over a fine‑tuning‑matched baseline, while reducing GSM8K errors by 46%.
By Thea Aviss
arXiv:2606. 18089v1 Announce Type: new Abstract: Post-training pipelines that combine supervised fine-tuning (SFT) with reinforcement learning (RL) have emerged as the key recipe for transforming large language models (LLMs) into robust reasoners.
By Lingjing Kong, Xin Liu, Guangyi Chen, Martin Q. Ma, Xiangchen Song, Yuekai Sun, Mikhail Yurochkin, Taylor W. Killian, Ruslan Salakhutdinov, Kun Zhang, Eric P. Xing, Zhengzhong Liu
arXiv:2601. 15158v4 Announce Type: replace-cross Abstract: Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought).
By Yuval Ran-Milo, Yotam Alexander, Shahar Mendel, Nadav Cohen