{"ID":2873198,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.08150","arxiv_id":"2509.08150","title":"Verbalized Algorithms: Classical Algorithms are All You Need (Mostly)","abstract":"Reasoning is a fundamentally algorithmic task. Yet current work on LLM-based reasoning relies on free-form generation whose theoretical guarantees (soundness, completeness, complexity, optimality) remain poorly understood. We argue that we should not treat them as general-purpose reasoners, and as an alternative, we propose a paradigm we call \\emph{verbalized algorithms} (VAs), which combines LLMs and various algorithms with established guarantees. Instead of betting on LLM's ability to solve a reasoning task, VAs limit their scope by decomposing the task down to simple elementary operations on strings that they can answer reliably. For example, sorting a list of natural language strings could be done by using an LLM as a binary comparison oracle in a parallel or approximate sorting algorithm. We push the accuracy-runtime Pareto front with \\emph{verbalized maximum}, \\emph{sorting}, \\emph{clustering}, and \\emph{submodular maximization}, for numerical reasoning, topic clustering, Wi-Fi access point optimization, and multi-hop Q\\\u0026A RAG task. These results suggest improving LLM-based reasoning through standard algorithmic analysis is a feasible and better grounded research direction.","short_abstract":"Reasoning is a fundamentally algorithmic task. Yet current work on LLM-based reasoning relies on free-form generation whose theoretical guarantees (soundness, completeness, complexity, optimality) remain poorly understood. We argue that we should not treat them as general-purpose reasoners, and as an alternative, we pr...","url_abs":"https://arxiv.org/abs/2509.08150","url_pdf":"https://arxiv.org/pdf/2509.08150v6","authors":"[\"Supriya Lall\",\"Christian Farrell\",\"Hari Pathanjaly\",\"Marko Pavic\",\"Sarvesh Chezhian\",\"Masataro Asai\"]","published":"2025-09-09T21:14:44Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false}