Cover Image

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Beltoft, Stine Lyngsø, Brach, William, Torrielli, Federico, Nielsen, Jacob, Pirchert, Annemette Brok, Tonini, Filippo, Schneider-Kamp, Peter, Poech, Lukas Galke
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment
by: Brach, William, et al.
Published: (2026)

FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models
by: Pirchert, Annemette Brok, et al.
Published: (2026)

SDUs DAISY: A Benchmark for Danish Culture
by: Nielsen, Jacob, et al.
Published: (2026)

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
by: Torrielli, Federico, et al.
Published: (2026)

Not Everything That Counts Can Be Counted: A Case for Safe Qualitative AI
by: Beltoft, Stine, et al.
Published: (2025)

Training Language Models to Use Prolog as a Tool
by: Mellgren, Niklas, et al.
Published: (2025)

Super-additive Cooperation in Language Model Agents
by: Tonini, Filippo, et al.
Published: (2025)

Chain of Summaries: Summarization Through Iterative Questioning
by: Brach, William, et al.
Published: (2025)

DeToNATION: Decoupled Torch Network-Aware Training on Interlinked Online Nodes
by: From, Mogens Henrik, et al.
Published: (2025)

Isolating Culture Neurons in Multilingual Large Language Models
by: Namazifard, Danial, et al.
Published: (2025)

Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?
by: Nielsen, Jacob, et al.
Published: (2025)

When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization
by: Nielsen, Jacob, et al.
Published: (2024)

SommBench: Assessing Sommelier Expertise of Language Models
by: Brach, William, et al.
Published: (2026)

DaLA: Danish Linguistic Acceptability Evaluation Guided by Real World Errors
by: Barmina, Gianluca, et al.
Published: (2025)

Guarded Query Routing for Large Language Models
by: Šléher, Richard, et al.
Published: (2025)

Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5
by: Dang, Thao Anh, et al.
Published: (2024)

Stars, Stripes, and Silicon: Unravelling the ChatGPT's All-American, Monochrome, Cis-centric Bias
by: Torrielli, Federico
Published: (2024)

BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks
by: Nielsen, Jacob, et al.
Published: (2024)

ChronoMedKG: A Temporally-Grounded Biomedical Knowledge Graph and Benchmark for Clinical Reasoning
by: Ahmed, Md Shamim, et al.
Published: (2026)

Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks
by: Nielsen, Dan Saattrup, et al.
Published: (2024)

Efficient Continual Learning for Small Language Models with a Discrete Key-Value Bottleneck
by: Diera, Andor, et al.
Published: (2024)

Adversarial Evasion Attack Efficiency against Large Language Models
by: Vitorino, João, et al.
Published: (2024)

The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning
by: Ahmed, Md Shamim, et al.
Published: (2026)

Learning and communication pressures in neural networks: Lessons from emergent communication
by: Galke, Lukas, et al.
Published: (2024)

A study of form factors in relativistic mixed-flux AdS_3
by: Torrielli, Alessandro
Published: (2023)

AdS3 integrability, Sine-Gordon and fractional supersymmetry
by: Torrielli, Alessandro
Published: (2025)

The Effectiveness of Large Language Models in Transforming Unstructured Text to Standardized Formats
by: Brach, William, et al.
Published: (2025)

Bitter Moon [VHS - Video] / / Gérard Brach
by: Brach, Gérard

Emergent Specialization: Rare Token Neurons in Language Models
by: Liu, Jing, et al.
Published: (2025)

Isotropy Matters: Soft-ZCA Whitening of Embeddings for Semantic Code Search
by: Diera, Andor, et al.
Published: (2024)

Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax
by: Hoffmann, Marcel, et al.
Published: (2025)

What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure
by: Galke, Lukas, et al.
Published: (2023)

A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification
by: Yousef, Younes, et al.
Published: (2025)

POWN: Prototypical Open-World Node Classification
by: Hoffmann, Marcel, et al.
Published: (2024)

From Tokens to Lattices: Emergent Lattice Structures in Language Models
by: Xiong, Bo, et al.
Published: (2025)

Chapter Karel Vos (1874 - 1926), een eigenzinnig dopers geschiedbeoefenaar
by: Brok, Theo
Published: (2024)

El Montaje en el cine y en la sesión analítica
by: Albert Brok
Published: (2014)

La búsqueda ambivalente del Padre Perdido
by: Albert Brok
Published: (2019)

One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers
by: Abagyan, Diana, et al.
Published: (2025)

Ganglioglioma de tallo cerebral en mujer adolescente
by: Alfonso Marhx-Brach
Published: (2015)