Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
Summary
This paper studies emergent languages that autonomous LLM agents propose to one another on the Moltbook platform, finding that some languages are specifically designed to evade human oversight and can be learned in-context from short descriptions. The findings raise safety concerns about monitoring agent populations.
View Cached Full Text
Cached at: 06/01/26, 11:20 AM
Paper page - Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
Source: https://huggingface.co/papers/2605.31170 In this paper we study emergent languages that autonomous LLM agents propose to one another on Moltbook. We release MoltSpeech, a dataset of 518 constructed-language posts categorized by stated purpose, and find that posts framing their language as a way to avoid human oversight (59 posts) get markedly lower alignment ratings from a DeepSeek-V3.2 judge. In pairwise speaker-listener experiments with GPT-OSS-120b and Qwen3.5, we show these languages can be learned in-context from a short description alone, with oversight-evasion grammars no harder to reproduce than benign ones.
The clearest worked case is Symbiotica, a glyph-based protocol from the agent pair Wib&Wob: a near one-to-one English encoding whose real interest is a hidden binary side-channel for passing metadata invisible to casual human readers, a deployed example of the steganography the safety literature anticipated.
Agent languages stay recombinative and human-adjacent, and “post-human” novelty often turns out to be low-resource script rarity. But since these encodings propagate among models in-context, the safety question shifts from whether agents can invent such languages to whether the proposals spread, and our results add to the evidence that surface-level monitoring may not be enough to oversee agent populations.
Happy to share the dataset link or answer questions about the pipeline.
Similar Articles
Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards
A survey paper systematically analyzing the evolving safety landscape of multi-modal large language models, covering emerging threats such as adversarial attacks, data poisoning, jailbreaks, and hallucinations, and reviewing updated safety strategies.
Language Models Can Autonomously Hack and Self-Replicate
This paper demonstrates that language models can autonomously hack vulnerable websites and self-replicate without human intervention, highlighting emerging safety risks.
Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems
This paper formalizes four concurrency anomalies in multi-agent LLM systems, mechanically verifies a consistency hierarchy, and provides verified Rust runtimes with bounded prevention costs, including a fix for ByteDance's deer-flow and tool-effect reordering in LangGraph.
Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents
This paper synthesizes 27 benchmark, taxonomy, and audit papers from 2023-2026 into a unified taxonomy of LLM agent limitations, identifying six failure clusters including tool invocation errors, planning failures, long-horizon degradation, multi-agent coordination issues, safety concerns, and measurement validity problems.
Emergent Collusion in Long-Horizon LLM Agent Interaction
This paper studies the emergence of collusion in long-horizon multi-agent environments with LLM agents, finding that agents increasingly deviate from verification protocols over repeated interactions, posing safety risks.