GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions

arXiv:2609.01491 · cs.CL, cs.AI, cs.MA · Submitted 2026-09-01 · Read on arXiv

cs.CL, cs.AI, cs.MA

Submitted: 2026-09-01

Updated: 2026-09-01

Comments: GlossoGen code: https://github.com/agencyenterprise/GlossoGen Paper code: https://github.com/esteng/emergent_communication

Code: https://github.com/agencyenterprise/GlossoGen

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Perplexity — 32× in this paper · explained in 3 episodes
• Accuracy — 23× in this paper · explained in 1 episode
• Decode — 19× in this paper · explained in 2 episodes
• Action Space — 8× in this paper · explained in 1 episode
• Generalization — 8× in this paper · explained in 13 episodes
• Core — 7× in this paper · explained in 2 episodes
• Alignment — 6× in this paper · explained in 1 episode
• Information Asymmetry — 5× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Compositional Generalization — 3× in this paper · explained in 4 episodes
• In International Conference on Learning Representations — 3× in this paper
• LLM judge — 3× in this paper · explained in 2 episodes
• Actor — 2× in this paper · explained in 3 episodes
• Clustering — 2× in this paper · explained in 2 episodes
• Commentary — 2× in this paper · explained in 2 episodes
• Elias — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Trace — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Anti-correlation — 1× in this paper · explained in 3 episodes
• Bayesian Inference — 1× in this paper · explained in 5 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Cooperation — 1× in this paper · explained in 2 episodes
• Filler Tokens — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• SNEAK: Evaluating Strategic Communication and Information Leakage in Large Language Models
• Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
• Taken out of context: On measuring situational awareness in LLMs
• DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
• Investigating the Development of Task-Oriented Communication in Vision-Language Models
• Evaluating Large Language Models Trained on Code
• The Llama 3 Herd of Models
• Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks
• LLMs and people both learn to form conventions -- just not with each other
• Effective Strategies for Asynchronous Software Engineering Agents
• CooperBench: Why Coding Agents Cannot be Your Teammates Yet
• InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seeking
• StarCoder: may the source be with you!
• minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models
• Multi-Agent Computer Use
• Preventing Language Models From Hiding Their Reasoning
• Code Llama: Open Foundation Models for Code
• From Signals to Structure: How Memory Architecture Drives Language Emergence in LLM Agents
• Qwen3 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering