arXiv AI July 28, 2026 By Xuening Wu, Qianya Xu, Yanlan Kang, Zeping Chen, Yubin Liu, Shenqin Yin

Do Language Models Converge to Themselves? Recursive Self-Refinement as Textual Relaxation

arXiv:2607. 22653v1 Announce Type: new Abstract: Large language models are increasingly used in recursive refinement workflows, where an initial draft is repeatedly revised by the same model.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

llms

arXiv Machine Learning

Jul 13

HALO: Hybrid Adaptive Latent Reasoning for Language Models

arXiv:2607. 08775v1 Announce Type: cross Abstract: We study how to improve a frozen pretrained language model with a small amount of adaptive extra computation.

By Micah Zhang

llms benchmarks

arXiv Machine Learning

Jul 31

LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints

arXiv:2410. 06458v2 Announce Type: replace-cross Abstract: Instruction following is a key capability for LLMs.

By Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, Nanyun Peng

llms benchmarks

arXiv AI

Jul 10

UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing

arXiv:2607. 08646v1 Announce Type: cross Abstract: As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish.

By Xinlong Zhao, Dongsheng Liu, Hengyu Zhao, Zixuan Fu, Zheng Wang, Jie Cai, Jie Zhou, Qiang Ma, Xuanhe Zhou, Xu Han, Yudong Wang, Zhiyuan Liu

llms safety

arXiv Machine Learning

Jul 23

LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization

arXiv:2407. 00740v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are widely adopted in real-world applications, it has become critical to ensure LLMs satisfy safety constraints, such as non-toxicity and logical consistency, as well as task- and situation-specific constraints.

By Hye Ryung Son, Saehee Eom, Mooho Song, Jay-Yoon Lee

llms rag safety

arXiv AI

Aug 5

Speculative Correction: Draft-then-Refine Decoding for Diffusion Language Models

arXiv:2608. 02625v1 Announce Type: cross Abstract: Diffusion language models (DLMs) can revise tokens bidirectionally, but standard decoding procedures often adapt them to left-to-right generation by producing text block by block.

By Brian K Chen, Chong Wu, Kenji Kawaguchi

llms diffusion

arXiv AI

Jun 29

Speculative Refinement: A Hybrid Autoregressive Diffusion Decoding Strategy and Its Behavior Across Benchmarks

arXiv:2606. 27474v1 Announce Type: cross Abstract: How should we evaluate generation systems that combine autoregressive (AR) and diffusion decoding?

By Aditi Gupta, Neel Mishra, Kushagra Trivedi, Pawan Kumar

llms diffusion benchmarks

Related stories

HALO: Hybrid Adaptive Latent Reasoning for Language Models

LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints

UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing

LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization

Speculative Correction: Draft-then-Refine Decoding for Diffusion Language Models

Speculative Refinement: A Hybrid Autoregressive Diffusion Decoding Strategy and Its Behavior Across Benchmarks