{"slug": "llm-agents-factory-retrieval-of-domain-specific-llm-agents", "title": "LLM Agents Factory: Retrieval of Domain-Specific LLM Agents", "summary": "Researchers introduced LLM Agents Factory, a retrieval-based framework that constructs domain-specific LLM agents on demand from a base of over 20,000 predetermined agent profiles, achieving accuracy comparable to AutoGen with a 120B backbone at lower inference cost. In experiments on MMLU, BIG-bench, and BIG-bench Hard, the retrieval-based approach outperformed non-agent baselines, offering a cost-efficient alternative for industrial applications. The implementation and agent base are available on Hugging Face.", "body_md": "arXiv:2608.09934v1 Announce Type: new\nAbstract: Large language model (LLM) agents improve task performance by decomposing problems into role-specialized behaviors. However, their practical deployment is often limited by the computational cost and instability associated with the on-the-fly agent design for each user request. To address this, we present LLM Agents Factory, a retrieval-based framework that constructs domain-specific and Wikipedia-grounded agents on demand using a base of over 20K predetermined agent profiles. Our framework supports two modes: (1) agent profile retrieval via semantic search and (2) distillation into a compact model fine-tuned for direct agent generation. Experiments on MMLU, BIG-bench, and BIG-bench Hard in a single-agent scenario demonstrate that our retrieval-based agent construction surpasses non-agent baselines in accuracy while matching AutoGen generation quality with a 120B backbone at a substantially lower inference cost. Our work reveals that retrieval from a structured agent repository provides a cost-efficient, accurate, and controllable alternative to dynamic agent generation, responding to the strict demands of industrial applications. We provide the implementation code and the agent base in https://huggingface.co/frontier-ai/llm-agent-factory.", "url": "https://wpnews.pro/news/llm-agents-factory-retrieval-of-domain-specific-llm-agents", "canonical_source": "https://arxiv.org/abs/2608.09934", "published_at": "2026-08-12 04:00:00+00:00", "updated_at": "2026-08-12 04:09:13.577661+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research"], "entities": ["LLM Agents Factory", "AutoGen", "MMLU", "BIG-bench", "BIG-bench Hard", "Hugging Face"], "alternates": {"html": "https://wpnews.pro/news/llm-agents-factory-retrieval-of-domain-specific-llm-agents", "markdown": "https://wpnews.pro/news/llm-agents-factory-retrieval-of-domain-specific-llm-agents.md", "text": "https://wpnews.pro/news/llm-agents-factory-retrieval-of-domain-specific-llm-agents.txt", "jsonld": "https://wpnews.pro/news/llm-agents-factory-retrieval-of-domain-specific-llm-agents.jsonld"}}