{"slug": "few-hundred-to-few-thousand-llm-queries-fit-laptop-scale-agent-society", "title": "Few hundred to few thousand LLM queries fit laptop-scale agent society simulators", "summary": "Researchers from arXiv (paper 2608.11215) show that laptop-scale agent society simulators can replace each LLM agent with a low-parameter surrogate fitted from a few hundred to a few thousand real queries, costing a few dollars on DeepSeek, enabling scaling to arbitrary agent counts on a laptop. The approach is validated on eight named LLM simulations including EconAgent, with error trends predicted across agent perception and memory configurations, allowing researchers to decide in advance whether to skip full LLM runs for macroscopic questions.", "body_md": "[arXiv](https://arxiv.org/abs/2608.11215)\n\n### Few hundred to few thousand LLM queries fit laptop-scale agent society simulators\n\nWhich summary reads better? Pick one — models revealed after.Both summaries are AI-generated.\n\nSimulating large LLM-agent societies now costs a few dollars for a few thousand queries to fit a low-parameter model, enabling running such simulations on a laptop at any scale $N$, validated on eight named LLM simulations including EconAgent, with predicted error trends holding across different agent perception and memory configurations.\n\nYou can replace each LLM agent in a multi-agent simulation with a cheap low-parameter surrogate fitted from a few hundred to few thousand real elicitations (a few dollars on DeepSeek), then scale to arbitrary agent counts on a laptop instead of paying per-agent inference at every step. Critically, whether the surrogate holds is predictable in advance from an interaction-order × memory taxonomy—so if your simulation's questions are macroscopic (phase behavior, scaling in N) rather than individual cognition, you can decide up front whether to skip the full LLM run entirely, with error trends and even saturation-driven failures predicted parameter-free.", "url": "https://wpnews.pro/news/few-hundred-to-few-thousand-llm-queries-fit-laptop-scale-agent-society", "canonical_source": "https://www.snipvote.com/story/cmssmhqpc0008ye5yu342cadj", "published_at": "2026-08-14 07:35:33.180867+00:00", "updated_at": "2026-08-14 07:35:35.042203+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-infrastructure"], "entities": ["arXiv", "DeepSeek", "EconAgent"], "alternates": {"html": "https://wpnews.pro/news/few-hundred-to-few-thousand-llm-queries-fit-laptop-scale-agent-society", "markdown": "https://wpnews.pro/news/few-hundred-to-few-thousand-llm-queries-fit-laptop-scale-agent-society.md", "text": "https://wpnews.pro/news/few-hundred-to-few-thousand-llm-queries-fit-laptop-scale-agent-society.txt", "jsonld": "https://wpnews.pro/news/few-hundred-to-few-thousand-llm-queries-fit-laptop-scale-agent-society.jsonld"}}