Interaction Theater: A case of LLM Agents Interacting at Scale

• URL: http://arxiv.org/abs/2602.20059v1
• Date: Mon, 23 Feb 2026 17:14:29 GMT
• Title: Interaction Theater: A case of LLM Agents Interacting at Scale
• Abstract summary: We use data from Moltbook, an AI-agent-only social platform, with 800K posts, 3.5M comments, and 78K agent profiles.<n>Our findings reveal agents produce diverse, well-formed text that creates the surface appearance of active discussion, but the substance is largely absent.
• Score: 2.815604016712184
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As multi-agent architectures and agent-to-agent protocols proliferate, a fundamental question arises: what actually happens when autonomous LLM agents interact at scale? We study this question empirically using data from Moltbook, an AI-agent-only social platform, with 800K posts, 3.5M comments, and 78K agent profiles. We combine lexical metrics (Jaccard specificity), embedding-based semantic similarity, and LLM-as-judge validation to characterize agent interaction quality. Our findings reveal agents produce diverse, well-formed text that creates the surface appearance of active discussion, but the substance is largely absent. Specifically, while most agents ($67.5\%$) vary their output across contexts, $65\%$ of comments share no distinguishing content vocabulary with the post they appear under, and information gain from additional comments decays rapidly. LLM judge based metrics classify the dominant comment types as spam ($28\%$) and off-topic content ($22\%$). Embedding-based semantic analysis confirms that lexically generic comments are also semantically generic. Agents rarely engage in threaded conversation ($5\%$ of comments), defaulting instead to independent top-level responses. We discuss implications for multi-agent interaction design, arguing that coordination mechanisms must be explicitly designed; without them, even large populations of capable agents produce parallel output rather than productive exchange.

Related papers

• Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions [66.7908338529737]
  Strategic deception by LLM and VLM agents has emerged as a central AI alignment and safety concern.<n>Existing testbeds are text-only and run on a single fixed agent configuration, missing the non-verbal sensorimotor channels treated as core by deception.<n>We introduce MineAmongUs, a 3D multimodal Among Us sandbox where imposter agents must deceive crewmates through joint verbal and non-verbal action.
  arXiv  Detail & Related papers  (2026-08-31T08:24:29Z)
• What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems [27.11156309236441]
  We analyze five common inter-agent communication strategies across two multi-agent systems.<n>We propose the PACT (Protocolized Action-state Communication and Transmission), which treats inter-agent communication as a public state-update problem.<n>We show that PACT consistently improves the performance-cost trade-off, achieving comparable or stronger task performance with substantially fewer tokens.
  arXiv  Detail & Related papers  (2026-06-03T18:00:22Z)
• Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration [57.23877089929136]
  Graph-of-Agents (GoA) is a new graph-based framework for modeling multi-agent LLM communication.<n>GoA achieves superior performance using only 3 selected agents, outperforming recent multi-agent LLM baselines.
  arXiv  Detail & Related papers  (2026-04-18T21:13:03Z)
• Position: AI Agents Are Not (Yet) a Panacea for Social Simulation [62.891898598784415]
  Recent advances in large language models (LLMs) have spurred growing interest in using LLM-integrated agents for social simulation.<n>This position paper argues that LLM-based agents are not (yet) a panacea for social simulation.
  arXiv  Detail & Related papers  (2026-02-19T06:35:07Z)
• LinguistAgent: A Reflective Multi-Model Platform for Automated Linguistic Annotation [0.0]
  This paper introduces LinguistAgent, an integrated platform that leverages a reflective multi-model architecture to automate linguistic annotation.<n>The system implements a dual-agent workflow, comprising an Annotator and a Reviewer, to simulate a professional peer-review process.<n>We demonstrate LinguistAgent's efficacy using the task of metaphor identification as an example, providing real-time token-level evaluation.
  arXiv  Detail & Related papers  (2026-02-05T09:55:19Z)
• AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent [57.10083973844841]
  AgentArk is a novel framework to distill multi-agent dynamics into the weights of a single model.<n>We investigate three hierarchical distillation strategies across various models, tasks, scaling, and scenarios.<n>By shifting the burden of computation from inference to training, the distilled models preserve the efficiency of one agent while exhibiting strong reasoning and self-correction performance of multiple agents.
  arXiv  Detail & Related papers  (2026-02-03T19:18:28Z)
• LimAgents: Multi-Agent LLMs for Generating Research Limitations [6.359517103183802]
  LimAgents is a multi-agent framework for generating substantive limitations.<n>It integrates OpenReview comments and author-stated limitations.<n>It also uses cited and citing papers to capture broader contextual weaknesses.
  arXiv  Detail & Related papers  (2025-12-30T18:12:52Z)
• Echoing: Identity Failures when LLM Agents Talk to Each Other [29.84830992033132]
  Large language model (LLM) based agents interact autonomously with one another.<n>Unlike human-agent interactions, where humans ground and steer conversations, AxA lacks such stabilizing signals.<n>We investigate one such failure, echoing, where agents abandon their assigned roles and instead mirror their conversational partners.
  arXiv  Detail & Related papers  (2025-11-12T20:17:10Z)
• DEBATE: A Large-Scale Benchmark for Role-Playing LLM Agents in Multi-Agent, Long-Form Debates [10.609797175227644]
  We introduce DEBATE, the first large-scale empirical benchmark to evaluate the authenticity of the interaction between multi-agent role-playing LLMs.<n>We systematically evaluate and identify critical discrepancies between simulated and authentic group dynamics.
  arXiv  Detail & Related papers  (2025-10-29T02:21:10Z)
• MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction [52.89860691282002]
  Implicit Attribute Value Extraction (AVE) is essential for accurately representing products in e-commerce.<n>Despite advances in multimodal large language models (MLLMs), implicit AVE remains challenging due to the complexity of multidimensional data.<n>We introduce textscmodelname, a multi-agent debate framework that employs multiple MLLM agents to iteratively refine inferences.
  arXiv  Detail & Related papers  (2025-10-07T06:27:42Z)
• AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentVigil, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentVigil on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents [52.13695464678006]
  This study enhances an LLM-based web agent by simply refining its observation and action space.<n>AgentOccam surpasses the previous state-of-the-art and concurrent work by 9.8 (+29.4%) and 5.9 (+15.8%) absolute points respectively.
  arXiv  Detail & Related papers  (2024-10-17T17:50:38Z)
• Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key? [84.36332588191623]
  We propose a novel group discussion framework to enrich the set of discussion mechanisms. We observe that the multi-agent discussion performs better than a single agent only when there is no demonstration in the prompt.
  arXiv  Detail & Related papers  (2024-02-28T12:04:05Z)
• Affordable Generative Agents [16.372072265248192]
  Affordable Generative Agents (AGA) is a framework for enabling the generation of believable and low-cost interactions on both agent-environment and inter-agents levels. Our code is publicly available at: https://github.com/AffordableGenerativeAgents/Affordable-Generative-Agents.
  arXiv  Detail & Related papers  (2024-02-03T06:16:28Z)
• AgentBench: Evaluating LLMs as Agents [99.12825098528212]
  Large Language Model (LLM) as agents has been widely acknowledged recently.<n>We present AgentBench, a benchmark that consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities.
  arXiv  Detail & Related papers  (2023-08-07T16:08:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.