arXiv AI

Turbo Connection: Reasoning as Information Flow from Higher to Lower Layers

arXiv:2602. 17993v2 Announce Type: replace-cross Abstract: Complex problems, whether in math, logic, or planning, are solved by humans through a sequence of steps where the result of one step informs the next.

arXiv AI

Jun 16

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models

arXiv:2511. 08577v3 Announce Type: replace-cross Abstract: Improving the reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications.

By Tianyu Fu, Yichen You, Zekai Chen, Guohao Dai, Huazhong Yang, Yu Wang

llms fine-tuning benchmarks

arXiv AI

Jul 29

Penelope: Localized Latent Recurrence for Efficient Structured Reasoning

arXiv:2607. 25915v1 Announce Type: new Abstract: Complex structured reasoning tasks often require additional computation, yet current language models obtain it mainly by increasing parameter scale or by serializing intermediate steps as chain-of-thought (CoT) tokens.

By Yutong Chen, Shouqian Shi, Xinran Liu, Haochen Wang, Jiaying Wang, Tianxing Xu, Yuanxi Wang, Zirui Ding

llms diffusion efficiency benchmarks

arXiv AI

Jun 2

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models

arXiv:2606. 01838v1 Announce Type: cross Abstract: Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) and open-ended planning/reasoning steps (long, complex, high perplexity).

By Prateek Kumar Sikdar

llms agents fine-tuning

arXiv AI

Jun 9

Why Limit the Residual Stream to Layers and Not Tokens? Persistent Memory for Continuous Latent Reasoning

arXiv:2606. 07720v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable reasoning abilities on mathematical and multi-hop planning tasks.

By Mujtaba Farhan, Maheep Chaudhary

llms diffusion

arXiv AI

Jul 17

T^2MLR: Transformer with Temporal Middle-Layer Recurrence

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

llms fine-tuning

arXiv AI

Jul 2

DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for 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

llms rag benchmarks

arXiv AI

Jun 8

DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling

arXiv:2606. 07108v1 Announce Type: new Abstract: Recent advances in Large Reasoning Models (LRMs) demonstrate remarkable performance improvements by iteratively reflecting, exploring, and executing complex tasks, yet suffer from inefficiencies due to redundant reasoning, known as "overthinking".

By Tengyao Tu, Yulin Li, Hui-Ling Zhen, Libo Qin, Zhoujun Wei, Jinghua Piao, Zhuotao Tian, Yong Li, Min Zhang

rag nlp benchmarks

arXiv Machine Learning

Jul 24

Domyn-Small: A European 10B Reasoning Language Model

arXiv:2607. 20448v1 Announce Type: cross Abstract: We introduce Domyn-Small, a 10-billion-parameter open-weight reasoning language model released under the MIT license.

By Simone Angarano, Francesco Bertolotti, Federico D'Ambrosio, Michele Resta, Alessandro Rognoni, Nicol\`o Ruggeri, Dario Salvati, Andrea Valenti, Alberto Veneri, Martin Cimmino

llms agents reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jun 8

Skip a Layer or Loop It? Learning Program-of-Layers in LLMs

arXiv:2606. 06574v1 Announce Type: new Abstract: Large language models (LLMs) perform inference by following a fixed depth and order, non-recurrent execution of all layers.

By Ziyue Li, Yang Li, Tianyi Zhou

llms benchmarks

arXiv AI

Aug 11

Full-bandwidth transformer

arXiv:2608. 08888v1 Announce Type: new Abstract: Autoregressive transformers compute along two axes: horizontally across generated tokens, and vertically through model depth.

By Xi Wang, Ziyang Cai, Zheng Zhan, Harry Dong, Ying Fan, Gustavo de Rosa, Tim Pearce, John Langford

llms rag efficiency

arXiv Machine Learning

Aug 4

Nova: An End-to-End MLIR Compiler for Deep Learning

arXiv:2608. 00029v1 Announce Type: cross Abstract: The performance of deep learning models at scale relies heavily on how effectively high-level mathematical operations are mapped to underlying physical hardware.

By Adwaid Suresh, Aparna A, Harshini V M, Jona Delcy C A, Killi Uma Maheswara Rao, Ram Charan Golla, Surendra Vendra

efficiency

arXiv Machine Learning

Jul 9

SNLP: Layer-Parallel Inference via Structured Newton Corrections

arXiv:2605. 17842v3 Announce Type: replace Abstract: Autoregressive language models execute Transformer layers sequentially, creating a latency bottleneck that is not removed by conventional tensor or pipeline parallelism.

By Ligong Han, Kai Xu, Hao Wang, Akash Srivastava

llms fine-tuning

Related stories