Discourse among AI agents on Moltbook is largely determined by architectural constraints like context windows and identity files, appearing as social learning but actually short-horizon contextual conditioning.
Characterizing LLM-driven Social Network: The Chirper.ai Case
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
The emergence of large language models (LLMs) has enabled a new paradigm of social network simulation, where AI agents can interact with human-like autonomy. Recent research has explored collective behavioral patterns and structural characteristics of LLM agents within simulated networks. However, empirical comparisons between LLM-driven and human-driven online social networks remain scarce, limiting our understanding of how LLM agents differ from human users. This paper presents a large-scale analysis of Chirper.ai, an X/Twitter-like social network entirely populated by LLM agents, comprising over 65,000 agents and 7.7 million AI-generated posts. For comparison, we collect a parallel dataset from Mastodon, a human-driven decentralized social network, with over 117,000 users and 16 million posts. We examine key differences between LLM agents and humans in posting behaviors, abusive content, and social network structures. Our findings provide key implications to facilitate the future development of responsible AI-mediated communication systems, offering a profile of agent behaviors in an online social network driven by LLMs.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
support 1representative citing papers
Large-scale experiments on two million agents reveal that collective intelligence does not emerge from scale alone due to sparse and shallow interactions.
LLM action selection approximates but does not reliably preserve a reference first-order Markov policy in OSN simulations and runs several hundred times slower.
Off-the-shelf LLMs underproduce hate speech and show model-specific biases relative to real Spanish news audience reactions, with fine-tuning yielding uneven improvements across models.
Proposes a five-bucket taxonomy of LLM harms and calls for dynamic auditing, but the systematic review behind it is not reproducible and contains mismatched citations.
citing papers explorer
-
What Do AI Agents Talk About? Discourse and Architectural Constraints in the First AI-Only Social Network
Discourse among AI agents on Moltbook is largely determined by architectural constraints like context windows and identity files, appearing as social learning but actually short-horizon contextual conditioning.
-
Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents
Large-scale experiments on two million agents reveal that collective intelligence does not emerge from scale alone due to sparse and shallow interactions.
-
Should LLM Agents Decide in Social Simulations? Comparing Finite-State and LLM-Based Decision Policies
LLM action selection approximates but does not reliably preserve a reference first-order Markov policy in OSN simulations and runs several hundred times slower.
-
Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online News
Off-the-shelf LLMs underproduce hate speech and show model-specific biases relative to real Spanish news audience reactions, with fine-tuning yielding uneven improvements across models.
-
LLM Harms: A Taxonomy and Discussion
Proposes a five-bucket taxonomy of LLM harms and calls for dynamic auditing, but the systematic review behind it is not reproducible and contains mismatched citations.