An approach for systematic decomposition of complex llm tasks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 5 of its 15 references that are in the map. First posted on arXiv 9 Oct 2025.
Builds on
5 of 15 references.
References · 5
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
- 2024Executable Code Actions Elicit Better LLM Agentscited by 564
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
- 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
- 2025SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulascited by 33
Built on by
Not cited yet.