arXiv AI September 18, 2026 By Alexander Shirnin, Aleksey Kudelya

For Your Eyes Only: Evaluating Coordination Between Isolated Language Model Instances

For Your Eyes Only: Evaluating Coordination Between Isolated Language Model Instances explores whether a language model can embed a signal in natural language that another independent instance can detect without shared memory or coordination training. The study introduces a cooperative signalling game where a Sender describes two words, one hidden, and a Receiver must identify the target. Seven contemporary models from four architectural families were tested on 300 word pairs, revealing that most struggle to coordinate when signals must be undetectable, though one frontier model performs near-perfectly even after filtering, and that models can also use this capability for deliberate misdirection.

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 AI.

llms

Hugging Face Trending Papers

Jul 22

Exposure is Optional: Learning Unlike Coordination in Language Models

Coordination, a fundamental linguistic structure, remains a subject of intense debate, and its exact nature continues to elude theoretical linguistics. A common view holds that only same-category constituents can be conjoined, which has been challenged by the many grammatical unlike coordinations found in natural language.

llms

arXiv Machine Learning

Jun 17

Tacit Coordination of Large Language Models

arXiv:2601. 22184v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in multi-agent settings that require coordination without communication, from human-AI interaction to safety-critical scenarios.

By Ido Aharon, Emanuele La Malfa, Michael Wooldridge, Sarit Kraus

llms agents safety

arXiv AI

Sep 3

Language Models Can Control Their Own Attention

The paper introduces Declarative Attention (DA), a protocol that lets language models explicitly declare which parts of their context to focus on during generation. By partitioning decoding into full-context, region-specific, and recent-output-only modes, the inference engine can skip large portions of the KV cache, dramatically reducing attended tokens. Experiments on 15 long-context tasks with off-the-shelf models show significant savings (52.0% and 31.1% reductions) with only modest accuracy drops that diminish as model size increases.

By Namgyu Ho, Huzama Ahmad, Woosung Koh, Se-Young Yun, Tal Schuster, Cicero Nogueira dos Santos

llms efficiency

arXiv Machine Learning

Jul 7

The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices

arXiv:2603. 18482v2 Announce Type: replace-cross Abstract: Standard decoding strategies for text generation, including top-$k$, nucleus sampling, and contrastive search, select tokens based on likelihood, restricting outputs to high-probability regions.

By Esteban Garces Arias, Nurzhan Sapargali, Christian Heumann, Matthias A{\ss}enmacher

llms safety

arXiv Computation and Language

Sep 15

Where Should Language Sit in a Multimodal Model? Lessons from What Language Does to Human Perception and Cognition

arXiv:2609.07474v2 Announce Type: replace Abstract: Language models compute over tokens: language is their input, their output, and increasingly their internal representation. Whether language should...

By Peng Xie, Amr Alanwar

llms robotics multimodal safety

arXiv AI

Aug 25

Measuring Activation Control in Large Language Models

arXiv:2608.21664v1 Announce Type: new Abstract: Safe deployment of increasingly capable models will likely come to rely on latent-space monitoring as a complement to behavioral evaluations, especiall...

By Marek Mateusz Kowalski, Joshua Fonseca Rivera, Uzay Macar, David Demitri Africa

llms diffusion benchmarks