{"ID":2857897,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.07772","arxiv_id":"2510.07772","title":"An approach for systematic decomposition of complex llm tasks","abstract":"Large Language Models (LLMs) suffer from reliability issues on complex tasks, as existing decomposition methods are heuristic and rely on agent or manual decomposition. This work introduces a novel, systematic decomposition framework that we call Analysis of CONstraint-Induced Complexity (ACONIC), which models the task as a constraint problem and leverages formal complexity measures to guide decomposition. On combinatorial (SAT-Bench) and LLM database querying tasks (Spider), we find that by decomposing the tasks following the measure of complexity, agent can perform considerably better.","short_abstract":"Large Language Models (LLMs) suffer from reliability issues on complex tasks, as existing decomposition methods are heuristic and rely on agent or manual decomposition. This work introduces a novel, systematic decomposition framework that we call Analysis of CONstraint-Induced Complexity (ACONIC), which models the task...","url_abs":"https://arxiv.org/abs/2510.07772","url_pdf":"https://arxiv.org/pdf/2510.07772v3","authors":"[\"Tianle Zhou\",\"Jiakai Xu\",\"Guanhong Liu\",\"Jiaxiang Liu\",\"Haonan Wang\",\"Eugene Wu\"]","published":"2025-10-09T04:24:47Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}