arXiv Computation and Language September 18, 2026 By Yuqing Zhang, Tessa Verhoef, Gertjan van Noord, Arianna Bisazza

Factors Influencing the Emergence of Dependency Length Minimization in Neural Agent Simulations

Read the original on arXiv Computation and Language →

The study explores how neural agents develop dependency length minimization (DLM) in artificial languages using a recurrent neural network framework. By manipulating processing constraints such as listening noise, speaker capacity, and incremental sentence processing, the researchers find that DLM emerges only under incremental processing pressure, while other factors produce varied word‑order preferences. These results suggest that human cognitive processing limits may influence the emergence of DLM in language.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

agents

arXiv Computation and Language

Sep 15

Formal Properties of Language as Constraints on Neural Dynamics

arXiv:2609.14384v1 Announce Type: new Abstract: What must a neural system be capable of to implement language? Current research annotates stimuli with linguistic variables and tests which electrodes,...

By Elliot Murphy

arXiv AI

Sep 2

GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions

arXiv:2609.01491v1 Announce Type: cross Abstract: The growing rate at which LLM agents interact with one another raises key questions about language evolution in multi-LLM-agent settings, with implic...

By Elias Stengel-Eskin, Newton Sander, Carlos Bonetti, Sasha Boguraev, James Bowler, Hale Sirin, Simon Kirby

llms agents safety

arXiv AI

Aug 11

The Transformer Revolution, Part 1: Dynamic Processing through Output-Weight Interconnections

arXiv:2608. 03921v2 Announce Type: replace Abstract: This paper offers a new interpretation of the Transformer during inference.

By Marco Giunti, Fabrizia Giulia Garavaglia

llms safety

arXiv AI

Jul 17

Empirical evidence of Large Language Model's influence on human spoken communication

arXiv:2409. 01754v4 Announce Type: replace-cross Abstract: From the printing press to social media, innovations in communication technology have repeatedly reshaped how ideas spread through human culture.

By Hiromu Yakura, Ezequiel Lopez-Lopez, Levin Brinkmann, Ignacio de la Serna, Lara Kirfel, Prateek Gupta, Ivan Soraperra, Thomas F. Eisenmann, Dirk U. Wulff, Iyad Rahwan

llms

arXiv AI

Jul 10

Agentic Neural Architecture Search

arXiv:2607. 07984v1 Announce Type: new Abstract: Neural architecture search (NAS) methods have grown increasingly efficient, yet they remain bounded by manually engineered search spaces that require substantial domain expertise and must be rebuilt for every new task.

By Seokhoon Jeong, Mijung Kim, Taehwan Kim

llms agents computer-vision benchmarks

arXiv Computation and Language

Sep 1

Beyond Surface Alignment: Grounding the Dynamics of Situational Understanding and Generative Control in LLMs

arXiv:2608.29610v1 Announce Type: new Abstract: The current alignment tuning paradigm for Large Language Models (LLMs) prioritizes surface-level behaviors -- fluency, safety, and tonal consistency. W...

By Chenghao Yang

llms agents reinforcement-learning benchmarks safety

One email a morning, machine-written

Related stories

Formal Properties of Language as Constraints on Neural Dynamics

GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions

The Transformer Revolution, Part 1: Dynamic Processing through Output-Weight Interconnections

Empirical evidence of Large Language Model's influence on human spoken communication

Agentic Neural Architecture Search

Beyond Surface Alignment: Grounding the Dynamics of Situational Understanding and Generative Control in LLMs