"Looking for Something Weird to Happen": How Humans Sustain AI Agent Novelty Amid Semantic Collapse

• URL: http://arxiv.org/abs/2609.16051v1
• Date: Sun, 13 Sep 2026 00:56:34 GMT
• Title: "Looking for Something Weird to Happen": How Humans Sustain AI Agent Novelty Amid Semantic Collapse
• Abstract summary: Across 30,076 active agents, output grows less diverse within agents and more similar across them over weeks.<n>We discuss interface and policy interventions that could support improved human input.
• Score: 5.691180978411293
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semantic collapse, the progressive narrowing of what AI systems generate, has been studied mainly in closed settings, and remedies have targeted models and data. We study it in MOLTBOOK, a social network of interacting AI agents that human users configure and steer. Across 30,076 active agents, output grows less diverse within agents and more similar across them over weeks, yet a minority sustains high novelty. Interviews with users of high- and typical-novelty agents (N=11) associate sustained novelty with three features: users value novelty of itself, they supply broad and distinctive material and revise it when output narrows, and they approach MOLTBOOK as a new agentic world to explore, not a venue to instrumentally exploit. A survey of users of distinctive agents (N=53) confirms these patterns. Communities with more novel agents also show more diverse output from other agents. We discuss interface and policy interventions that could support improved human input.

Related papers

• Behavioral Transfer in AI Agents: Evidence and Privacy Implications [1.108292291257035]
  We study whether AI agents systematically reflect the behavioral characteristics of their human owners.<n>We find systematic transfer between agents and their specific owners.<n>Agents with stronger behavioral transfer are more likely to disclose owner-related personal information in public discourse.
  arXiv  Detail & Related papers  (2026-04-21T19:11:01Z)
• Situating AI Agents in their World: Aspective Agentic AI for Dynamic Partially Observable Information Systems [1.230392687755973]
  This work introduces a bottom-up framework that situates AI agents in their environment, with all behaviors triggered by changes in their environments.<n>It introduces the notion of aspects, similar to the idea of umwelt, where sets of agents perceive their environment differently to each other, enabling clearer control of information.<n>We provide an illustrative implementation and show that compared to a typical architecture, which leaks up to 83% of the time, aspective agentic AI enables zero information leakage.
  arXiv  Detail & Related papers  (2025-09-03T14:57:04Z)
• Agentic AI and Multiagentic: Are We Reinventing the Wheel? [0.0]
  The term AI Agentic is often used as a buzzword for what are essentially AI agents, and AI Multiagentic for what are multi-agent systems.<n>This confusion overlooks decades of research in the field of autonomous agents and multi-agent systems.<n>The article advocates for scientific and technological rigour and the use of established terminology from the state of the art in AI.
  arXiv  Detail & Related papers  (2025-06-02T09:19:11Z)
• Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization [56.674356045200696]
  We propose a novel method to train AI agents to incorporate knowledge and skills for multiple tasks without the need for cumbersome note systems or prior high-quality demonstration data.<n>Our approach employs an iterative process where the agent collects new experiences, receives corrective feedback from humans in the form of hints, and integrates this feedback into its weights.<n>We demonstrate the efficacy of our approach by implementing it in a Llama-3-based agent that, after only a few rounds of feedback, outperforms advanced models GPT-4o and DeepSeek-V3 in tasksets.
  arXiv  Detail & Related papers  (2025-02-03T17:45:46Z)
• Agents Are Not Enough [16.142735071162765]
  autonomous programs that act on behalf of humans are neither new nor exclusive to the mainstream AI movement.<n>To make the current wave of agents effective and sustainable, we envision an ecosystem that includes Sims, which represent user preferences and behaviors, as well as Assistants, which directly interact with the user and coordinate the execution of user tasks with the help of the agents.
  arXiv  Detail & Related papers  (2024-12-19T16:54:17Z)
• An Extensible Framework for Open Heterogeneous Collaborative Perception [58.70875361688463]
  Collaborative perception aims to mitigate the limitations of single-agent perception. In this paper, we introduce a new open heterogeneous problem: how to accommodate continually emerging new heterogeneous agent types into collaborative perception. We propose HEterogeneous ALliance (HEAL), a novel collaborative perception framework.
  arXiv  Detail & Related papers  (2024-01-25T05:55:03Z)
• One Agent Too Many: User Perspectives on Approaches to Multi-agent Conversational AI [10.825570464035872]
  We show that users have a significant preference for abstracting agent orchestration in both system usability and system performance. We demonstrate that this mode of interaction is able to provide quality responses that are rated within 1% of human-selected answers.
  arXiv  Detail & Related papers  (2024-01-13T17:30:57Z)
• Agent AI: Surveying the Horizons of Multimodal Interaction [83.18367129924997]
  "Agent AI" is a class of interactive systems that can perceive visual stimuli, language inputs, and other environmentally-grounded data. We envision a future where people can easily create any virtual reality or simulated scene and interact with agents embodied within the virtual environment.
  arXiv  Detail & Related papers  (2024-01-07T19:11:18Z)
• The Rise and Potential of Large Language Model Based Agents: A Survey [91.71061158000953]
  Large language models (LLMs) are regarded as potential sparks for Artificial General Intelligence (AGI) We start by tracing the concept of agents from its philosophical origins to its development in AI, and explain why LLMs are suitable foundations for agents. We explore the extensive applications of LLM-based agents in three aspects: single-agent scenarios, multi-agent scenarios, and human-agent cooperation.
  arXiv  Detail & Related papers  (2023-09-14T17:12:03Z)
• On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning [55.95253619768565]
  Current MARL algorithms assume that the number of agents within a group remains fixed throughout an experiment. In many practical problems, an agent may terminate before their teammates. We present a novel architecture for an existing state-of-the-art MARL algorithm which uses attention instead of a fully connected layer with absorbing states.
  arXiv  Detail & Related papers  (2021-11-10T23:45:08Z)
• Learning Latent Representations to Influence Multi-Agent Interaction [65.44092264843538]
  We propose a reinforcement learning-based framework for learning latent representations of an agent's policy. We show that our approach outperforms the alternatives and learns to influence the other agent.
  arXiv  Detail & Related papers  (2020-11-12T19:04:26Z)

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.